From efipatm at gmail.com Fri Nov 1 06:29:04 2024 From: efipatm at gmail.com (Efi) Date: Fri, 1 Nov 2024 12:29:04 +0200 Subject: Connectionists: =?utf-8?q?Join_the_AIIA/AIDA_free_short_e-course_?= =?utf-8?q?=E2=80=9CBig_Data_Analytics_for_Natural_Disaster_Managem?= =?utf-8?b?ZW504oCdLCAzLzEyLzIwMjQu?= Message-ID: Dear AI/CS/ECE student/scientist/engineer/enthusiast, the Artificial Intelligence and Information Analysis (AIIA ) Lab of Aristotle University of Thessaloniki (AUTH) in cooperation with the International AI Doctoral Academy (AIDA ), is excited to invite you to register and attend the online short course ?*Big Data Analytics for Natural Disaster Management* ?. ? *Date*: December 3, 2024 ? *Time*: 08:35 - 19:30 EET (09:35 - 20:30 CET) This course offers ten in-depth lectures on the following cutting-edge topics: - Drone Imaging - Computer Vision - Image Segmentation - Object Detection - Privacy Protection - Simulation and Modeling of Natural Disasters - Big Data Analytics - Cloud Computing - Multimodal Data Analysis ? *Join via Zoom*: [Zoom Link ] ? *Passcode*: 114050 *?** Register now*: Please register in advance in this course* for free *through the above-mentioned short course www page and find more details. For AIDA students only: On the top of the above registration, we strongly encourage you to also enroll in this course through the AIDA website , so that a successful attendance of this course appears in the AIDA Certificate of Course Attendance. Students/Scientists, Engineers from other scientific disciplines having the necessary mathematical background are also welcomed to register. This short course is organized by the Horizon Europe R&D project TEMA , and is part of the e-2024 ?AIIA/AIDA Winder School on ?AI and big Data Analytics for Inspection/Surveillance, Disaster Prevention and Management ?. We look forward to your participation! School Organizer: Prof. Ioannis Pitas Chair of the International AI Doctoral Academy (AIDA), Director of the Artificial Intelligence and Information analysis (AIIA) Lab, Aristotle University of Thessaloniki, Greece -------------- next part -------------- An HTML attachment was scrubbed... URL: From stdm at zhaw.ch Fri Nov 1 10:56:41 2024 From: stdm at zhaw.ch (Stadelmann Thilo (stdm)) Date: Fri, 1 Nov 2024 14:56:41 +0000 Subject: Connectionists: CfP SDS 2025: The IEEE Swis Conferen on Data Science (Deadline: Feb 07, 2025) Message-ID: Dear colleagues, please consider submitting original research work at the intersection of AI, data science, and applications to the IEEE SDS 2025, to be held in Zurich, Switzerland, on June 26-27, 2025. Specifically, address central questions such as: * What novel developments in AI, machine learning, data representations, and computing frameworks and tools can open new application domains? * Which interesting applications challenge the state of the art? * Which applications address the most urgent societal or business needs but currently lack efficient solutions? We invite original research submissions focusing on novelty, best practice and use case orientation. Submissions are required to demonstrate both scientific-technical depth and practical applicability, encompassing methods along the full pipeline of data science and AI systems - from data acquisition and data management, through data analysis using machine learning and artificial intelligence (AI), to visualization, data product design, and the management of societal effects. Topics of Interest Topics include but are not limited to, the following key focus areas for 2025: * Large Language and Foundation Models * Human-AI Interaction * AI and Data Analytics for Science * AI and Society There are short (4 pages, IEEE 2-column format) and long papers (8 pages) are accepted. All accepted publications will by published by IEEE on IEEE Xplore. The acceptance rate of 2024 was ~35%. Important dates: Submission deadline: February 7, 2025 Review until: March 20, 2025 Rebuttal Period: March 31 - April 4 2025 Decision Notification: April 16, 2025 Please find the full call for papers here: https://mcusercontent.com/de4b4a6f3f2494d677593a7f4/files/5e9ab53c-6e46-106b-2163-3e36b6863f74/SDS2025_CallforPapers.pdf Best, Thilo ------------------------------------------------------------------------------------------------------------- ZHAW School of Engineering Prof. Dr. Thilo Stadelmann, FECLT, SMIEEE [aktuell abwesend als Gastprofessor an der Universit?t Z?rich, Institut f?r Neuroinformatik, bis Februar 2025] Zentrumsleiter Centre for Artificial Intelligence Leiter Machine Perception and Cognition Group Tel: +41 58 934 72 08, Fax: +41 58 935 72 08 Email: thilo.stadelmann at zhaw.ch Web: www.zhaw.ch/cai, http://stdm.github.io B?ro: TN 03.64, Technikumstrasse 71, CH-8400 Winterthur Postanschrift: ZHAW School of Engineering, Thilo Stadelmann, Postfach, 8401 Winterthur, Schweiz Lageplan: https://www.zhaw.ch/storage/shared/hochschule/lageplaene/lageplan-winterthur-technikumstrasse.pdf -------------- next part -------------- An HTML attachment was scrubbed... URL: From aurel at ee.columbia.edu Fri Nov 1 14:34:36 2024 From: aurel at ee.columbia.edu (Aurel A. Lazar) Date: Fri, 1 Nov 2024 14:34:36 -0400 Subject: Connectionists: Olfactory research needs to shift from solely focusing on processing syntactic (or Shannon) information to processing semantic, i.e., odorant identity information Message-ID: <8624DD34-0D01-4CAA-A510-F56FC8721438@ee.columbia.edu> Most of the experiments in the olfactory literature, assume that the odorant identity is known. As such, prior arts have primarily focused on the representation of odorant syntactic information (i.e., concentration amplitude) and cannot, therefore, serve as baseline methods without a formal computational/theoretic model of odorant identity. In contrast we argue in the paper below that odor signal processing in the Early Olfactory System of the fruit fly, is mostly focussed on extracting semantic information. Consequently, we assert that olfactory research needs to shift from solely focusing on processing syntactic (or Shannon) information to processing semantic, i.e., odorant identity information. Modeling and characterization of pure and odorant mixture processing in the Drosophila mushroom body calyx Aurel A. Lazar, Tingkai Liu, Chung-Heng Yeh and Yiyin Zhou https://doi.org/10.3389/fphys.2024.1410946? Frontiers | Modeling and characterization of pure and odorant mixture processing in the Drosophila mushroom body calyx doi.org Results in brief: (i) Odorant stimuli are modeled by their identity (semantics) and concentration amplitude (syntactic) information content. (ii) The Antennal Lobe and Calyx jointly separate the odorant semantics from syntactic information. (iii) The semantics info is mapped by the Calyx into a first spike sequence for easy memory access in the Mushroom Body. Aurel http://www.bionet.ee.columbia.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: fphys-15-1410946-g001.jpg Type: image/jpeg Size: 475534 bytes Desc: not available URL: From pfbaldi at ics.uci.edu Fri Nov 1 11:26:55 2024 From: pfbaldi at ics.uci.edu (Baldi,Pierre) Date: Fri, 1 Nov 2024 08:26:55 -0700 Subject: Connectionists: A Theory of Synaptic Neural Balance Message-ID: https://arxiv.org/abs/2405.09688 From david at irdta.eu Sat Nov 2 03:44:55 2024 From: david at irdta.eu (David Silva - IRDTA) Date: Sat, 2 Nov 2024 08:44:55 +0100 (CET) Subject: Connectionists: DeepLearn 2025: early registration November 26 Message-ID: <1257506491.2096612.1730533495436@webmail.strato.com> ****************************************************** 12th INTERNATIONAL SCHOOL ON DEEP LEARNING (with a special focus on Large Language Models, Foundation Models and Generative AI) DeepLearn 2025 Porto ? Maia, Portugal July 21-25, 2025 https://deeplearn.irdta.eu/2025/ ****************************************************** Co-organized by: University of Maia Institute for Research Development, Training and Advice ? IRDTA Brussels/London ****************************************************** Early registration: November 26, 2024 ****************************************************** SCOPE: DeepLearn 2025 will be a research training event with a global scope aiming at updating participants on the most recent advances in the critical and fast developing area of deep learning. Previous events were held in Bilbao, Genova, Warsaw, Las Palmas de Gran Canaria, Guimar?es, Las Palmas de Gran Canaria, Lule?, Bournemouth, Bari, Las Palmas de Gran Canaria and Porto. Deep learning is a branch of artificial intelligence covering a spectrum of current frontier research and industrial innovation that provides more efficient algorithms to deal with large-scale data in a huge variety of environments: computer vision, neurosciences, speech recognition, language processing, human-computer interaction, drug discovery, biomedicine and health informatics, medical image analysis, recommender systems, advertising, fraud detection, robotics, games, business and finance, biotechnology, physics experiments, biometrics, communications, climate sciences, geographic information systems, signal processing, genomics, materials design, video technology, social systems, earth and sustainability, etc. etc. The field is also raising a number of relevant questions about robustness of the algorithms, explainability, transparency, interpretability, as well as important ethical concerns at the frontier of current knowledge that deserve careful multidisciplinary discussion. Most deep learning subareas will be displayed, and main challenges identified through 18 four-hour and a half courses, 2 keynote lectures, 1 round table and a hackathon competition among participants. Renowned academics and industry pioneers will lecture and share their views with the audience. The organizers are convinced that outstanding speakers will attract the brightest and most motivated students. Face to face interaction and networking will be main ingredients of the event. It will be also possible to fully participate in vivo remotely. DeepLearn 2025 will place special emphasis on large language models, foundation models and generative artificial intelligence. ADDRESSED TO: Graduate students, postgraduate students and industry practitioners will be typical profiles of participants. However, there are no formal pre-requisites for attendance in terms of academic degrees, so people less or more advanced in their career will be welcome as well. Since there will be a variety of levels, specific knowledge background may be assumed for some of the courses. Overall, DeepLearn 2025 is addressed to students, researchers and practitioners who want to keep themselves updated about recent developments and future trends. All will surely find it fruitful to listen to and discuss with major researchers, industry leaders and innovators. VENUE: DeepLearn 2025 will take place in Porto, the second largest city in Portugal, recognized by UNESCO in 1996 as a World Heritage Site. The venue will be: University of Maia Avenida Carlos de Oliveira Campos - Cast?lo da Maia 4475-690 Maia Porto, Portugal https://www.umaia.pt/en STRUCTURE: 3 courses will run in parallel during the whole event. Participants will be able to freely choose the courses they wish to attend as well as to move from one to another. All lectures will be videorecorded. Participants will be able to watch them again for 45 days after the event. An open session will give participants the opportunity to present their own work in progress in 5 minutes. Also companies will be able to present their technical developments for 10 minutes. The school will include a hackathon, where participants will be able to work in teams to tackle several machine learning challenges. Full live online participation will be possible. The organizers highlight, however, the importance of face to face interaction and networking in this kind of research training event. KEYNOTE SPEAKERS: Yonina Eldar (Weizmann institute of Science), Model Based AI and Applications Manuela Veloso (JPMorganChase), AI, Humans, and Robots for Task Solving PROFESSORS AND COURSES: (to be completed) Pierre Baldi (University of California Irvine), [intermediate/advanced] From Deep Learning and Transformers to AI Risks and Safety Sean Benson (Amsterdam University Medical Center), [intermediate] Digital Twins and Generative AI for Personalised Medicine Nello Cristianini (University of Bath), tba Mark Derdzinski (Dexcom), [introductory] From Prototype to Production: Evaluation Strategies for Agentic Applications Samira Ebrahimi Kahou (University of Calgary), [intermediate/advanced] Explainability in Machine Learning Elena Giusarma (Michigan Technological University), [introductory/intermediate] Machine Learning at the Frontier of Astrophysics: Simulating the Universe Shih-Chieh Hsu (University of Washington), [intermediate/advanced] Real-Time Artificial Intelligence for Science and Engineering Xia "Ben" Hu (Rice University), [introductory/advanced] Efficient LLM Serving: Algorithms, Systems and Applications Lu Jiang (ByteDance & Carnegie Mellon University), tba Jayashree Kalpathy-Cramer (University of Colorado), [introductory/intermediate] Multimodal AI for Healthcare Yingbin Liang (Ohio State University), [intermediate/advanced] Theory on Training Dynamics of Transformers Chen Change Loy (Nanyang Technological University), [intermediate/advanced] Harnessing Prior for Content Enhancement and Creation Preslav Nakov (Mohamed bin Zayed University of Artificial Intelligence), tba Evan Shelhamer (DeepMind), [intermediate] Test-Time Adaptation for Updating Models on New and Different Data Atlas Wang (University of Texas Austin), [intermediate] Low Rank Strikes Back in the Era of Large Language Models Xiang Wang (University of Science and Technology of China), [advanced] Large Language Models for User Behavior Modeling: Cross-Modal Interpretation, Preference Optimization, and Agentic Simulation Rex Ying (Yale University), [intermediate/advanced] Multimodal Foundation Models for Graph-Structured Data: Framework and Scientific Applications OPEN SESSION: An open session will collect 5-minute voluntary oral presentations of work in progress by participants. They should submit a half-page abstract containing the title, authors, and summary of the research to david at irdta.eu by July 13, 2025. INDUSTRIAL SESSION: A session will be devoted to 10-minute demonstrations of practical applications of deep learning in industry. Companies interested in contributing are welcome to submit a 1-page abstract containing the program of the demonstration and the logistics needed. People in charge of the demonstration must register for the event. Expressions of interest have to be submitted to david at irdta.eu by July 13, 2025. HACKATHON: A hackathon will take place, where participants can work in teams to tackle several machine learning challenges. They will be coordinated by Professor Sergei V. Gleyzer (University of Alabama). The challenges will be released 2 weeks before the beginning of the school. A jury will judge the submissions and the winners of each challenge will be announced by August 25, 2025. The winning teams will receive a modest monetary prize and the runners-up will get a certificate. SPONSORS: Companies/institutions/organizations willing to be sponsors of the event can download the sponsorship leaflet from https://deeplearn.irdta.eu/2025/sponsors/ ORGANIZING COMMITTEE: Sergei V. Gleyzer (Tuscaloosa, hackathon chair) Jos? Paulo Marques dos Santos (Maia, local chair) Carlos Mart?n-Vide (Tarragona, program chair) Sara Morales (Brussels) Jos? Lu?s Reis (Maia) Lu?s Paulo Reis (Porto) David Silva (London, organization chair) REGISTRATION: It has to be done at https://deeplearn.irdta.eu/2025/registration/ The selection of 6 courses requested in the registration template is only tentative and non-binding. For logistical reasons, it will be helpful to have an estimation of the respective demand for each course. Since the capacity of the venue is limited, registration requests will be processed on a first come first served basis. The registration period will be closed and the on-line registration tool disabled when the capacity of the venue will have got exhausted. It is highly recommended to register prior to the event. FEES: Fees comprise access to all program activities and lunches. There are several early registration deadlines. Fees depend on the registration deadline. The fees for on site and for online participation are the same. ACCOMMODATION: Accommodation suggestions will be available in due time at https://deeplearn.irdta.eu/2025/accommodation/ CERTIFICATE: A certificate of successful participation in the event will be delivered indicating the number of hours of academic activities. This should be sufficient for those participants who plan to request ECTS recognition from their home university. QUESTIONS AND FURTHER INFORMATION: david at irdta.eu ACKNOWLEDGMENTS: Universidade da Maia Universidade do Porto Universitat Rovira i Virgili Institute for Research Development, Training and Advice ? IRDTA, Brussels/London -------------- next part -------------- An HTML attachment was scrubbed... URL: From zitao.jerry.liu at gmail.com Sat Nov 2 09:48:37 2024 From: zitao.jerry.liu at gmail.com (Zitao Liu) Date: Sat, 2 Nov 2024 21:48:37 +0800 Subject: Connectionists: First Call for Papers - AI for Education@AAAI 2025 Message-ID: *The 6th International Workshop on AI for Education at AAAI 2025* ** Call for Papers ** - AAAI2025 The 6th International Workshop on AI for Education - Tools, Opportunities, and Risks in the Generative AI Era *http://ai4ed.cc/workshops/aaai2025 * The rapid advancement of generative AI technologies presents both unprecedented opportunities and significant challenges within the educational landscape. With tools like ChatGPT, DALL-E, and other generative models becoming increasingly sophisticated, educators have access to powerful resources that can enhance learning experiences, personalize education, and streamline administrative tasks. However, these advancements also bring forth critical issues such as ethical considerations, data privacy concerns, and potential biases. This workshop aims to explore how generative AI can be effectively and responsibly integrated into education, ensuring that its benefits are maximized while mitigating associated risks. --------------------- Workshop Description --------------------- In this workshop, we will invite AIED enthusiasts from all around the world through the following three different channels: First, we will invite established researchers in the AIED community to give a keynote talk that (1) describes a vision for bridging AIED communities; (2) summarizes a well-developed AIED research area; or (3) presents promising ideas and visions for new AIED research directions. Second, we will call for regular workshop paper submissions related to a broad range of AI domains for education. Third, we will host an AIED doctoral consortium that provides an opportunity for a group of Ph.D. students to discuss and explore their research interests and career objectives with a panel of established AIED researchers. Through these initiatives, we aim to provide a common ground for researchers to share their cutting-edge insights on AIED and encourage the development of practical and large-scale AIED methods of lasting impact. --------------------- Workshop Paper Submission --------------------- We invite high-quality paper submissions of a theoretical and experimental nature on generative AI topics including, but not limited to, the following: - Emerging technologies in education - Evaluation of education technologies - Immersive learning and multimedia applications - Self-adaptive learning - Individual and personalized education - Intelligent learning systems - Intelligent tutoring and monitoring systems - Automatic grading and assessment - Automated feedback and recommendations - Big data analytics for education - Analysis of communities of learning - Course development techniques - Data analytics & big data in education - Mining and web mining in education - Learning tools experiences and cases of study - Social media in education - Smart education - Digital libraries for learning - Knowledge management for learning - Learning technology for lifelong learning - Tracking learning activities - Wearable computing technology in e-learning - Smart classroom - Dropout prediction - Knowledge tracing The workshop solicits 5-7 pages double-blind paper submissions (with unlimited references) from participants. Submissions of the following flavors will be sought: (1) research ideas, (2) case studies (or deployed projects), (3) review papers, (4) best practice papers, and (5) lessons learned. The format is the standard double-column AAAI Proceedings Style. All submissions will be peer-reviewed. Some will be selected for spotlight talks, and some for the poster session. --------------------- Submission Website --------------------- Submission Template: https://aaai.org/authorkit25/ Papers can be submitted through the OpenReview link: https://openreview.net/group?id=AAAI.org/2025/Workshop/AI4EDU --------------------- Important Dates --------------------- Note: All deadlines are anywhere on earth (UTC-12) - Friday, November 22, 2024: Workshop Submissions Due - Monday, December 9, 2024: Notifications Sent to Authors - Thursday, December 19, 2024: AAAI-25 Early Registration Deadline - March 3, 2025: AAAI-25 AI4EDU Workshop Program --------------------- Organizers --------------------- - Zitao Liu, Guangdong Institute of Smart Education, Jinan University, China - John Stamper, Human-Computer Interaction Institute, Carnegie Mellon University, USA - Andrew M. Olney, Department of Psychology, University of Memphis, USA - Tianqiao Liu, TAL Education Group, China - Qingsong Wen, Squirrel AI Learning, USA Best Regards, The AI4EDU workshop organizing committees (Zitao, John, Andrew, Tianqiao and Qingsong) Dean of Guangdong Institute of Smart Education at Jinan University | Zitao Liu | http://www.zitaoliu.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From mingbo.cai at gmail.com Sat Nov 2 16:08:36 2024 From: mingbo.cai at gmail.com (Mingbo Cai) Date: Sat, 2 Nov 2024 16:08:36 -0400 Subject: Connectionists: Faculty position of AI and psychology/neuroscience - University of Miami Message-ID: The Department of Psychology at the University of Miami invites applications for a full-time, tenure-eligible, or tenure-track faculty member to join our department in August 2025. The opening is part of a College of Arts & Sciences cluster hire dedicated to artificial intelligence (machine learning). Prospective candidates should use artificial intelligence as a core approach in their investigations and/or as a topic of their research. Individuals who also have interests in computational approaches including advanced quantitative techniques are encouraged to apply. The specific area of research is open. Area(s) of focus could include, but are not limited to, basic research on perception, cognition, affect, neurophysiology, language, behavior, mental health, the impact of disparities, learning, development, human computer interaction, deep neural network mechanisms, brain-inspired AI, or computational cognitive neuroscience. The candidate?s research would complement and expand current work in the department using large language models to study naturalistic speech, using machine learning to model emotional communication, and using computational models to explain both neural processing and behavior. Candidates will support and advance UM?s mission to engage in innovative and interdisciplinary AI research across the college and university. The Department of Psychology is a vibrant, collaborative community that includes clinical and psychological sciences faculty across Adult , Cognitive and Behavioral Neuroscience , Child , and Health Divisions. The mission of the Department is to acquire, advance, and disseminate knowledge within the Psychological and Biobehavioral Sciences, supported through excellent graduate programs and state-of-the-art facilities. The department values and celebrates cultural diversity of all kinds and has an active Diversity and Equity Committee . The greater Miami community is one of the most ethnically and culturally diverse metropolitan areas in the country. Applications will be considered at all ranks. Appointment is expected to start on August 15, 2025. Candidates must hold a Ph.D. by the appointment start date. Applications can be submitted via the UM Careers Website . Please compile the following documents in *up to five PDFs (each within 5MB) and upload them under the Resume/CV *section of the online application. If you have difficulties uploading any representative publications due to size limitations, please email them directly to our administrative assistant Maria Shah (maria.shah at miami.edu). ? Letter of interest ? Current CV ? Research statement ? Teaching statement ? A statement that explains your contributions to diversity, equity, and inclusion, including comment on mentoring underrepresented populations ? 3 representative publications ? 3-4 references ? we will request letters of recommendation for a final pool of applicants Review of applications will begin on December 1, 2024 and continue until the position is filled. Inquiries, requests for information, and nominations can be sent to the Search Co-Chairs, Aaron Heller ( aheller at miami.edu) and Daniel Messinger (dmessinger at miami.edu). *------------------------------* The University of Miami is an Equal Opportunity Employer ? Females, Minorities, Protected Veterans, and/or Individuals with Disabilities are encouraged to apply. Applicants and employees are protected from discrimination based on certain categories protected by Federal law. Click here for additional information. Mingbo Cai Assistant Professor Department of Psychology University of Miami -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: PSY AI Search Miami Ad 2024-2025.pdf Type: application/pdf Size: 259087 bytes Desc: not available URL: From marinella.petrocchi at iit.cnr.it Sat Nov 2 13:07:40 2024 From: marinella.petrocchi at iit.cnr.it (Marinella Petrocchi) Date: Sat, 02 Nov 2024 18:07:40 +0100 Subject: Connectionists: [3rd CFP][ECIR 2025][Doctoral Consortium - Extended Deadline] In-Reply-To: <6e3a1d45181c9290b60b32554a14376a@iit.cnr.it> References: <6e3a1d45181c9290b60b32554a14376a@iit.cnr.it> Message-ID: <9581c45e241ef726d076a1712d58b1e9@iit.cnr.it> Doctoral Consortium @ECIR 2025: The 47th European Conference on Information Retrieval Lucca, Italy, April 6, 2025 Extended Deadline: Abstract due: November 10 2024, 11:59pm (AoE) Paper due: November 17 2024, 11:59pm (AoE) Doctoral Consortium website: https://ecir2025.eu/call-for-doctoral-consortium-papers/ Submission link: https://easychair.org/conferences/?conf=ecir2025 ECIR 25 Doctoral Consortium CHAIRS * Marinella Petrocchi (IIT-CNR, Pisa, Italy) * Gabriele Tolomei (Sapienza University of Rome, Italy) * Contact: ecir2025-dc at easychair.org From dhansel0 at gmail.com Sun Nov 3 18:00:43 2024 From: dhansel0 at gmail.com (David Hansel) Date: Mon, 4 Nov 2024 00:00:43 +0100 Subject: Connectionists: [seminar.wwtns] World wide VVTNS series: Wednesday, Wednesday 6, 2024, at 11:00 am EST In-Reply-To: References: Message-ID: [image: VVTNS.png] https://www.wwtns.online - on twitter: wwtns at TheoreticalWide You are cordially invited to the lecture given by Hannah Choi Georgia Tech on the topic of Unraveling information processing through functional networks The lecture will be held on zoom on Wednesday, November 6, 2024, at *11:00 am EST * To receive the zoom link: https://www.wwtns.online/register-page *Abstract: *While anatomical connectivity changes slowly through synaptic learning, the functional connectivity of neurons changes rapidly with ongoing activity of neurons and their functional interactions. Functional networks of neurons and neural populations reflect how their interactions change with behaviors, stimulus types, and internal states. Therefore, the information propagation across a network can be analyzed through the varying topological properties of the functional networks. Our study investigates the functional networks of the visual cortex at both the single-cell and population levels. Our analyses of functional connectivity of single neurons, constructed from spiking activity in neural populations of the visual cortex, reveal local and global network structures shaped by stimulus complexity. In addition, we propose a new method for inferring functional interactions between neural populations that preserves biologically constrained anatomical connectivity and signs. Applying our method to 2-photon data from the mouse visual cortex, we uncover functional interactions between cell types and cortical layers, suggesting distinct pathways for processing expected and unexpected visual information. *About VVTNS : Launched as the World Wide Theoretical Neuroscience Seminar (WWTNS) in November 2020 and renamed in homage to Carl van Vreeswijk in Memoriam (April 20, 2022), Speakers have the occasion to talk about theoretical aspects of their work which cannot be discussed in a setting where the majority of the audience consists of experimentalists. The seminars, **held on Wednesdays at 11 am ET,** are 45-50 min long followed by a discussion. The talks are recorded with authorization of the speaker and are available to everybody on our YouTube channel.* ? ? -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: VVTNS.png Type: image/png Size: 41084 bytes Desc: not available URL: From tt at cs.dal.ca Sun Nov 3 14:11:14 2024 From: tt at cs.dal.ca (Thomas Trappenberg) Date: Sun, 3 Nov 2024 15:11:14 -0400 Subject: Connectionists: Fwd: INNS: Register for Marco Gori's Webinar! In-Reply-To: References: Message-ID: 7 November 2024 - 14:00 UTC View this email in your browser INNS Webinar Series Towards lifelong learning intelligent agents capable of focusing attention and taking conscious actions - Neural Propagation in the Framework of Cognidynamics *7 November 2024 | **14:00 UTC* Register Now The fields of Artificial Intelligence (AI) and Cognitive Science began intersecting significantly during the Eighties when the Connectionist wave strongly propelled studies on Artificial Neural Networks. The evolution of AI over the last few decades, focusing on deep learning and, more recently, generative AI, has produced spectacular results that were hardly predictable even by the pioneers of the discipline. However, when examining early studies on Connectionism, many aspirations remain unrealized, as most successful outcomes rely on the brute force of combining computational resources with large data collections. This stands in contrast to nature, where cognition emerges from environmental interactions and the processing of temporal information. In order to capture those natural processes and explore an alternative path to Machine Learning, in this talk I introduce the framework of Cognidynamics that describes cognitive systems whose environmental interactions are driven by the minimization of a functional over time. This functional, referred to as cognitive action, replaces the traditional statistical functional risk of Machine Learning in the temporal dimension. I employ the tools of Theoretical Physics and Optimal Control to derive unified laws of cognition for learning and inference in recurrent neural networks. I demonstrate that Hamiltonian equations, in their causal dissipative form, lead to a novel neural propagation scheme that is local in both space and time. This addresses the longstanding debate on the biological plausibility of Backpropagation and offers a new framework for developing lifelong learning intelligent agents capable of focusing attention and taking conscious actions. *Marco Gori* Siena Artificial Intelligence Lab University of Siena Marco Gori received the Ph.D. degree in 1990 from Universit? di Bologna, Italy, working partly at the School of Computer Science (McGill University, Montreal). He is currently full professor of computer science at the University of Siena, where he is leading the Siena Artificial Intelligence Lab. He is mostly interested in Machine Learning with emphasis on Neural Computation. The impact of his research on neural networks emerged mainly from the growing interest in Graph Neural Networks. He introduced the first ideas in the paper ?A New Model for Learning in Graph Domains?, by M. Gori, M. Monfardini and F. Scarselli (IJCNN2005) where the keyword Graph Neural Network was coined. A few years later, the most significant paper ?Graph Neural Networks,? IEEE-TNN, 2009 provided a more robust analysis and an accurate experimental evaluation. To date, the paper has received about 9,000 citations (about 6-7 citations/day in the last months). Professor Gori has been the chair of the Italian Chapter of the IEEE Computation Intelligence Society and the President of the Italian Association for Artificial Intelligence. He is a Fellow of IEEE, EurAI, IAPR, and ELLIS. Register Now [image: LinkedIn] LinkedIn [image: Twitter] Twitter [image: YouTube] YouTube [image: Website] Website *Copyright ? 2024 International Neural Network Society, All rights reserved.* You are receiving this email because of your membership in International Neural Network Society. *Our mailing address is:* International Neural Network Society 2720 NW 6th St Gainesville, FL 32609-2994 Add us to your address book Want to change how you receive these emails? You can update your preferences or unsubscribe from this list . Forward to a Friend -------------- next part -------------- An HTML attachment was scrubbed... URL: From rbianchi at fei.edu.br Mon Nov 4 12:46:26 2024 From: rbianchi at fei.edu.br (Reinaldo A. C. Bianchi) Date: Mon, 4 Nov 2024 17:46:26 +0000 Subject: Connectionists: Call for Participation - RoboCup Humanoide Competition 2025 @ Salvador, Brazil. Message-ID: <320AFF61-E44E-4EB1-9EB7-9C9180F5B06D@fei.edu.br> * Call for Participation * RoboCup 2025 Humanoid Soccer Competition https://humanoid.robocup.org/ July 15 - 21, 2025, Salvador, Brazil =========================================================== The RoboCup Humanoid League invites teams to apply for participation at the RoboCup 2025 Humanoid Soccer Competition in Salvador, Brazil. The Humanoid League will host competitions in the following categories: * KidSize: 40 - 100cm robot height (FIFA size 1 ball) * AdultSize: 100 - 200cm robot height (FIFA size 5 ball) For more detailed class definitions, please refer to the humanoid league home page at https://humanoid.robocup.org/. Teams do not need to provide a full robot team to apply for competing in the Humanoid Soccer Competition. The qualifying round of Drop-In games will be played with only one robot per team. Teams that cannot provide a full team of robots (four robots in KidSize and two in AdultSize) will be grouped to form a playable team for the main tournament games. Teams are also encouraged to form and apply as joint teams. Joint proposals will be judged on their combined merit. In case of a sufficient number of qualified teams, the sub-leagues (KidSize and/or AdultSize) will be divided into League A and League B. Teams are seeded into the leagues based on the results of an initial round of Drop-In games. For the qualification process, teams must provide the following material: 1) Robot Video --------------------------------------- Teams need to provide a video of their robot demonstrating the robots' autonomous soccer playing skills. The recommended skills needed for qualification are: * localization of unknown ball position, * walking ability towards the ball, * robot positioning at the ball for kicking, * kicking the ball towards the goal, * ability of getting up autonomously from a fall (KidSize only) We encourage teams to include in the video more complex and intelligent behavior such as demonstrating localization, and robots playing in a game, recordings from actual soccer matches are admissible. If possible, please provide footage that demonstrates the robot behavior without wires attached. The qualification video must be supplied as a link via YouTube. The maximum duration of the video must not exceed 5 minutes. The qualifying team is responsible to ensure that the video adheres to YouTube's TOS (especially in regard to music copyright) to prevent the video from being blocked for the reviewers. Teams that do not provide a qualification video or a viewable video will not be qualified! 2) Software Description --------------------------------------- During the registration process, a form will be provided to submit details about the algorithms used or anticipated to be used for the participation in the 2025 competition. Algorithms shall be described in such detail that they can be reproduced by other teams. If software from other teams or standard algorithms are used, references need to be included. If the algorithm has been adapted to be used in the competition, those deviations need to be described in appropriate details. The form will include questions in the following areas: * Walking * Vision * Localization * Team Communication * Behavior * Contributions to the RoboCup community, e.g. software releases, paper publications, provision of league infrastructure or data sets Responses to the questions are expected to reflect the current or anticipated status of the software during the RoboCup 2025 competition. If the software has not changed or no changes are anticipated to be made until the competition, teams may copy & paste a response from previously submitted material. 3) Extended Abstract --------------------------------------- A two-page extended abstract must be submitted. For teams which have previously participated in the Humanoid League, the extended abstract needs to: * include lessons learned from the participation in previous RoboCup competitions * highlight major problems that the team is trying to solve for the upcoming competition * outline the plans for the major changes that the teams anticipate to have implemented by the RoboCup 2025 competition * describe the implementation status of the changes planned by the time of submitting the application For teams which have never participated in the RoboCup Humanoid League, the Extended Abstract needs to pitch the scientific aspects of their humanoid robotic system and highlight their research interests. The Extended Abstract is limited to 2 pages maximum and must be submitted in PDF format. Extended Abstracts are designed to highlight the changes and scientific developments since the last RoboCup. Thus, we expect the usage of material from previous TDPs or Extended Abstracts to be minimal. If used, they need to be cited appropriately. Submissions of last year's Extended Abstract will be desk-rejected. The Extended Abstract must follow the LNCS format which can be downloaded from https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines. Teams that do to follow the LNCS formatting and style guidelines will not be qualified. No exceptions to this rule will be made. 4) Robot Specification --------------------------------------- Regardless of the kid or adult size competition, a one-page specification (PDF) must be provided for each different type of humanoid robot used by the team that includes the following: * Robot picture * Robot name * Height of the robot * Weight of the robot * Walking speed in cm/s * Number of degrees of freedom and type of motors on each kinematic chain of the robot * Type of sensors used (incl. type of camera(s) and specific manufacturer part number (e.g. ?6-DoF IMU? is NOT an acceptable description)) * Computing unit(s) * Materials (e.g. Torso aluminum, legs and arms CFRP) * Electronics (e.g. CM730 for communicating with servos) * Battery (e.g. 3S1P 2200mAh LiPo) * Open Source link if applicable * Other specs 5) Letter of Commitment --------------------------------------- A one-page letter addressed to the RoboCup Humanoid League Technical Committee including the following: * a statement committing to participate in the RoboCup 2025 Humanoid League competition, * a statement committing to make a person with sufficient knowledge of the rules available as referee during the competition. The letter must be signed (by hand or using a digital signature software as Adobe or DocuSign) by the team leader and submitted either as a JPG, PNG or PDF file. The TC may include the fulfillment of the statement of commitment of participation as well as the performance of the team's referee in previous RoboCup competitions into consideration for qualification. Each application to the Humanoid Soccer Competition will be reviewed by two members of the Technical Committee and two other teams applying to the Humanoid Soccer Competition. The combined reviewing score will decide whether a team qualifies for participation. Reviewing other team's material is mandatory for teams that want to participate in the Humanoid Soccer Competition. Failing to provide an adequate review by the provided deadline will have consequences for the team?s own qualification status. 6) Rules --------------------------------------- The current version of the rules may be found here at the Humanoid League website: https://humanoid.robocup.org/materials/rules/. We expect the final version of the 2025 rules to be published in early spring 2025. 7) Registration --------------------------------------- The following information is required for registration: * Team name * URL of the team's home page * Name of team leader or team contact person * E-mail address of team leader or contact person * Postal address of the team, team leader or contact person * Competition category: Humanoid Soccer Competition KidSize or AdultSize Please note that teams applying for participation in several categories must submit individual application material for each class, and pay the appropriate registration fee for each category. At least one team member must register on each team. Furthermore, teams in different categories must be able to compete, and guarantee to have members acting as referees available independently and at the same time. 8) Plagiarism ======================================= Plagiarism, loosely the unattributed use of other peoples' words, code, and ideas is not tolerated in the RoboCup community. See the point "Publishing Ethics" at https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines for a more detailed description. The teams and team members that plagiarize another peoples' work and present it as their own will be disqualified. For a first offense, the team and team members will be banned from RoboCup competition for two years (usually the current and next year). Harsher penalties will be applied to repeat offenders or extremely serious cases of plagiarism. A team may be disqualified at any time for plagiarism, even after the competition has started. RoboCup will not reimburse teams for any expenses related to their disqualification. 9) Online Submission ======================================= All qualification material must be submitted online. The submission site is still under development and will be made available on the next days. 10) Important Dates ======================================= Humanoid Soccer Competition * Submission system open: November 17th, 2024 * Submission deadline: December 13th, 2024 * Team Review Period: December 16th - December 20th, 2024 * Announcement of qualified teams: January 17th, 2025 11) Publication ======================================= Please note that after the announcement of the qualified teams the qualified teams submitted material will be made publicly available on the Humanoid League website. Teams applying for participation, therefore, implicitly grant the right of publication of their qualification material to the Humanoid League. 12) Visa Process ======================================= If you are a citizen of a country that needs a Visa for traveling to the Netherlands, please start the VISA process as soon as you receive your notification of qualification. If you are not sure if you're eligible for a VISA-exempt, please consult the official website of the Brazilian government for information, at https://www.gov.br/mre/pt-br/assuntos/portal-consular/vistos/informacoes-sobre-vistos-para-estrangeiros-viajarem-ao-brasil. For more information about the humanoid league, please refer to the humanoid league home page at https://humanoid.robocup.org/ and join the humanoid league mailing list at: https://lists.robocup.org/listinfo/robocup-humanoid With best regards, Technical Committee of RoboCup Humanoid League 2025 Esta mensagem, juntamente com qualquer outra informa??o anexada, ? confidencial e protegida por lei. Somente os seus destinat?rios est?o autorizados a us?-la. Se voc? n?o for o destinat?rio, por favor, informe o remetente e, em seguida, apague a mensagem, observando que n?o h? autoriza??o para usar, copiar, armazenar, encaminhar, imprimir ou tomar qualquer a??o baseada no seu conte?do. -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Mon Nov 4 21:36:45 2024 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 04 Nov 2024 18:36:45 -0800 Subject: Connectionists: NEURAL COMPUTATION - November 1, 2024 In-Reply-To: Message-ID: NEURAL COMPUTATION - Volume 36, Number 11 - November 1, 2024 Now available for online download: http://www.mitpressjournals.org/toc/neco/36/11 http://cognet.mit.edu/content/neural-computation ----- Review Predictive Representations: Building Blocks of Intelligence Sam Gershman, Wilka Carvalho, Momchil S. Tomov, William de Cothi, and Caswell Barry Articles Spiking Neural Network Pressure Sensor Micha? Markiewicz, Ireneusz Brzozowski, and Szymon Janusz Prototype Analysis in Hopfield Networks With Hebbian Learning Hayden Robert McAlister, Anthony Robins, and Lech Szymanski Deep Nonnegative Matrix Factorization With Beta Divergences Nicolas Gillis., Nicolas Gillis., Valentin Leplat, Le T.K. Hien, and Akwum Onwunta Deconstructing Deep Active Inference: A Contrarian Information Gatherer Th?ophile Champion, Marek Grze?, Lisa Bonheme, and Howard Bowman Latent Space Bayesian Optimization With Latent Data Augmentation for Enhanced Exploration Ichiro Takeuchi, Onur Boyar Multi-Modal and Multi-Factor Branching Time Active Inference Th?ophile Champion, Howard Bowman, and Marek Grze? Letters Learning Internal Representations of 3D Transformations From 2D Projected Inputs Marissa Connor, Bruno Olshausen, Chris Rozell L1-Regularized ICA: A Novel Method for Analysis of Task-related fMRI Data Koujin Takeda, Yusuke Endo ----- ON-LINE -- http://www.mitpressjournals.org/neco MIT Press Journals, One Rogers Street, Cambridge, MA 02142-1209 Tel: (617) 253-2889 FAX: (617) 577-1545 journals-cs at mit.edu ----- From emergingtechnetwork.publicity at gmail.com Mon Nov 4 17:21:59 2024 From: emergingtechnetwork.publicity at gmail.com (Gizem Varkonyi) Date: Tue, 5 Nov 2024 01:21:59 +0300 Subject: Connectionists: ICSC 2025 CFP: The Fifth Intelligent Cybersecurity Conference, Tampa, Florida, USA. May 19-22, 2025 Message-ID: [Apologies if you got multiple copies of this invitation] The Fifth Intelligent Cybersecurity Conference (ICSC2025) Hybrid Event https://www.icsc-conference.org/2025/ Tampa, Florida, USA. May 19-22, 2025 Technically Co-Sponsored by IEEE Florida West Coast Section *ICSC 2025 CFP:* In today?s world, connected systems, social networks, and mobile communications create a massive flow of data, which is prone to cyberattacks. This needs fast and accurate detection of cyber-attacks. Intelligent systems and Data analytics are important components when issues pertaining to effective security solutions become the subject of discussion. This is because there is an impending need for high volume and high velocity data from different sources to detect anomalies as soon as they are discovered. This will help reduce significantly the vulnerability of the systems as well as improve their resilience to cyber Attacks. The capability to process large volumes of information at real time through utilization of tools for data analytics has many advantages vital for analysis of cybersecurity systems. Moreover, the data collected from sophisticated intelligent systems, cloud systems, networks, sensors, computers, intrusion detection systems could be used to identify vital information. This information could be used to detect how vulnerable the systems are to risk factors, and so effective cyber security solutions can be developed. In addition to that, the utilization of data analytics tools in the cybersecurity field gives new insights through considering factors such as zero-day attack detection, real time analysis, resource constrained data processing among others. The Intelligent Cybersecurity Conference (ICSC) addresses the use of advanced intelligent systems in providing cybersecurity solutions in many fields, and the challenges, approaches, and future directions. We invite the submission of original papers on all topics related to Intelligent Systems for Cybersecurity, with special interest in but not limited to: - Intelligent systems for effective detection of cyber-attacks - Advanced Intelligent systems and data analytics for Cloud/Edge systems security - Malware detection using intelligent systems Vulnerability assessment - Intelligent systems for intrusion detection in Internet of Things (IoT) systems - Network forensics using intelligent systems and data analytics - Data Analytics for privacy-by-design in smart health - Datasets, benchmarks, and open-source packages - Recourse efficient deep learning - Adversarial Machine learning and Backdoor Attacks - Blockchain Systems for Cyber Security - Trustworthy AI Systems - Intelligent Systems for Misinformation Detection *Submissions Guidelines and Proceedings* Manuscripts should be prepared in 10-point font using the IEEE 8.5" x 11" two-column format. All papers should be in PDF format, and submitted electronically at Paper Submission Link. A full paper can be up to 8 pages (including all figures, tables and references). Submitted papers must present original unpublished research that is not currently under review for any other conference or journal. Papers not following these guidelines may be rejected without review. Also submissions received after the due date, exceeding length limit, or not appropriately structured may also not be considered. Authors may contact the Program Chair for further information or clarification. All submissions are peer-reviewed by at least three reviewers. Accepted papers will appear in the ICSC Proceeding, and be published by the IEEE Computer Society Conference Publishing Services and be submitted to IEEE Xplore for inclusion. Submitted papers must include original work, and must not be under consideration for another conference or journal. Submission of regular papers up to 8 pages and must follow the IEEE paper format. Please include up to 7 keywords, complete postal and email address, and fax and phone numbers of the corresponding author. Authors of accepted papers are expected to present their work at the conference. Submitted papers that are deemed of good quality but that could not be accepted as regular papers will be accepted as short papers. Length of short papers can be up to 6 pages. *Important Dates:* - *Paper submission deadline: Jan 15th 2025* - Notification of acceptance: April 1st, 2025 - Camera-ready Submission: April 21st, 2025 *Contact:* Please send any inquiry on ICSC to Fahed Alkhabbas at: fahed.alkhabbas at mau.se -------------- next part -------------- An HTML attachment was scrubbed... URL: From evomusart at gmail.com Mon Nov 4 17:51:15 2024 From: evomusart at gmail.com (EvoMUSART) Date: Mon, 4 Nov 2024 22:51:15 +0000 Subject: Connectionists: =?utf-8?q?Extended_Submission_Deadline_=E2=80=94_?= =?utf-8?q?EvoMUSART_2025?= Message-ID: Call for papers for the 14th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART) ? Please distribute ? Apologies for cross-posting ------------------------------------------------ The 14th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART) will take place on 23-25 April 2025, as part of the evo* event. *EvoMUSART webpage:* www.evostar.org/2025/evomusart/ *Extended Submission deadline: *1 November 2024 *Conference: *23-25 April 2024 EvoMUSART is a multidisciplinary conference that brings together researchers who are working on the application of Artificial Neural Networks, Evolutionary Computation, Swarm Intelligence, Cellular Automata, Alife, and other Artificial Intelligence techniques in creative and artistic fields such as Visual Art, Music, Architecture, Video, Digital Games, Poetry, or Design. This conference gives researchers in the field the opportunity to promote, present and discuss ongoing work in the area. Submissions must be at most 14 pages long, excluding references, in Springer LNCS format. Each submission must be anonymized for a double-blind review process. Accepted papers will be presented orally or as posters at the event and included in the EvoMUSART proceedings published by Springer Nature in a dedicated volume of the Lecture Notes in Computer Science series. Indicative topics include but are not limited to: - Systems that create drawings, images, animations, sculptures, poetry, text, designs, webpages, buildings, etc.; - Systems that create musical pieces, sounds, instruments, voices, sound effects, sound analysis, etc.; - Systems that create artefacts such as game content, architecture, furniture, based on aesthetic and functional criteria; - Robotic-based Evolutionary Art and Music; - Other related artificial or generative techniques in the fields of Computer Music, Computer Art, etc. - Techniques for automatic fitness assignment; - Systems in which an analysis or interpretation of the artworks is used in conjunction with artificial intelligence techniques to produce novel objects; - Systems that resort to artificial intelligence approaches to perform the analysis of image, music, sound, sculpture, or some other types of artistic object or resource. - Systems in which artificial intelligence is used to promote the creativity of a human user; - New ways of integrating the user in the evolutionary cycle; - Analysis and evaluation of: the artistic potential of biologically inspired art and music; the artistic processes inherent to these approaches; the resulting artefacts; - Collaborative distributed artificial art environments; - Contextualisation of creative AI in cultural, economic, social, political or ecological discourse; - Computational Aesthetics, Experimental Aesthetics; Emotional Response, Surprise, Novelty; - Representation techniques; - Surveys of the current state-of-the-art in the area; identification of weaknesses and strengths; comparative analysis and classification; - Validation methodologies; - Studies on the applicability of these techniques to related areas; - New models designed to promote the creative potential of biologically inspired computation. More information on the submission process and the topics of EvoMUSART: www.evostar.org/2025/evomusart/ Flyer of EvoMUSART 2025: http://www.evostar.org/2025/flyers/evomusart We look forward to seeing you in EvoMUSART 2025! The EvoMUSART 2025 organisers Penousal Machado Colin Johnson Iria Santos (publication chair) -------------- next part -------------- An HTML attachment was scrubbed... URL: