Connectionists: Deadline tomorrow: BMI Machine Conscious Learning Project

[Juyang Weng]

*BMI Machine Conscious Learning Project*

http://www.brain-mind-institute.org/program-summer.html

Ever since humankind came into being, holistic mechanisms of Natural
General Intelligence (NGI) and Artificial General Intelligence (AGI) have
been elusive. For example, the Third World Science and Technology
Development Forum Nov. 6-7, 2021 published "The Ten Scientific Problems for
the Development of Human Society for 2021". The No. 1 Problem in the
information domain is "what are the mechanisms for human brains to process
information and for generating human intelligence?" Many machine learning
experts hoped that NGI and AGI can be modeled by, or achieved by, training
increasingly larger neural networks on increasingly larger data sets that
are static, like well-known projects AlphaGo, AlphaZero, AlphaFold , the
IBM Debater and many other similarly large neural network projects
elsewhere. Unfortunately, such approaches are categorically hopeless for
AGI, not only because of the alleged Post Selection protocol flaws [
WengNatureProtocol21
<http://www.cse.msu.edu/~weng/research/2021-06-28-Report-to-Nature-specific-PSUTS.pdf>
,WengScienceProtocol21
<http://www.cse.msu.edu/~weng/research/2021-12-13-Science-AI-Papers-Post-Seleciton-Protocol.pdf>]
but something much deeper and more fundamental. The recent discovery of
Conscious Learning by Weng 2022 [WengCLICCE22
<http://www.cse.msu.edu/~weng/research/ConsciousLearning-ICCE-2022-rvsd-cite.pdf>
,WengCLAIEE22
<http://www.cse.msu.edu/~weng/research/ConsciousLearning-AIEE22rvsd-cite.pdf>]
revealed a surprising principle, namely consciousness is recursively
necessary across every time instant of learning by humans and machines in
order to reach their NGI and AGI at each corresponding mental age.

Consciousness, in the full sense as we know it and defined in dictionaries,
will never arise as an outcome of feeding static data sets, regardless of
how large the data sets are and what kinds of neural network we use. But
instead, consciousness is a necessary capability of a learner, natural or
artificial for NGI or AGI, so that conscious thinking takes place while the
learner processes information while learning across space and time on the
fly. Weng proposes that the algorithmic theory of Conscious Learning in [
WengCLICCE22
<http://www.cse.msu.edu/~weng/research/ConsciousLearning-ICCE-2022-rvsd-cite.pdf>
,WengCLAIEE22
<http://www.cse.msu.edu/~weng/research/ConsciousLearning-AIEE22rvsd-cite.pdf>]
supported by the Developmental Networks is the first holistic solution to
the above No. 1 Problem in the information domain.

Therefore, GNI appears to be computationally modeled and AGI seems to be
machine achievable.

The remaining challenges toward modeling NGI and achieving AGI are still
great but exciting. They include education of Conscious Learning theory and
algorithms; research on hardware design for real-time, brain size Conscious
Learning; development of practical Conscious Learning products; and
applications of Conscious Learning theory and algorithms.

BMI, the Brain-Mind Institute, is pleased to announce a funded Project,
called BMI Conscious Machine Learning Project, for all those who are
interested. This announcement calls for professors, graduate students, and
undergraduate students to apply for an appropriate position in the Project.
The open positions include the following three categories:

   1. *Research advisors*: There are four categories, assistant professors,
   associate professors, full professors and retired professors, corresponding
   to your current rank. The responsibilities include advising local students.
   It is desirable that each professor recruits a few of his students locally.
   Send your CV to BMI with the names, affiliations and contact information of
   the students who will submit applications in association with you. Each BMI
   paid student will correspond a part of budget for his research advisor.
   2. *Graduate students: *There are two categories, PhD program and MS
   program. Each student is expected to spend 10 hours each week during his
   university semesters and 40 hours each week during summer. The student's
   time spent on the projects will be paid by BMI at a rate suited for his own
   country. Each applicant should identify a local research advisor who
   supervises the project on a weekly basis. If you are a graduate student in
   a university and are interested in applying for the Project, find a
   professor in your local university who can supervise you. Ask him to
   jointly apply for a professor position at the Project. You two should name
   each other in the applications. Send your CV and official transcripts
   during the undergraduate years and the graduate years.
   3. *Undergraduate students: *There are four categories, freshmen,
   sophomore, junior and senior, corresponding to your year in your home
   university. Other requirements are similar to the Graduate student category.

Admission terms: summer session 2022 or fall 2022. Specify your preferred
starting summer date and fall date, as each country has a different date.

Send your filled application form
<http://www.brain-mind-institute.org/ApplicationForm-BMI-2022.doc>, your
application and supporting material to juyang.weng at gmail.com with a
subject: Application: BMI Conscious Machine Learning Project.

*Important dates:*
*January 15, 2022:* Deadline for application
*March 15, 2022:* Notice of admission

For further detail and questions, contact juyang.weng at gmail.com.

PDF file
<http://www.cse.msu.edu/~weng/research/2021-12-15-BMI-CL-Project.pdf>

-- 
Juyang (John) Weng
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20220114/ea273c26/attachment.html>