Connectionists: NEURAL COMPUTATION - March 1, 2019

[Terry Sejnowski]

Neural Computation - Volume 31, Number 3 - March 1, 2019

Available online for download now:

http://www.mitpressjournals.org/toc/neco/31/3
http://cognet.mit.edu/content/neural-computation

-----

Article

Gradient Descent with Identity Initialization Efficiently Learns 
Positive Definite Linear Transformations by Deep Residual Networks
Peter L. Bartlett, David P. Helmbold, and Philip M. Long

Letters

Forgetting Memories and Their Attractiveness
Enzo Marinari, Laurea

Scalable and Flexible Unsupervised Feature Selection
Haojie Hu, Rong Wang, Xiaojun Yang, and Feiping Nie

State Space Representations of Deep Neural Networks
Michael Hauser, Sean Gunn, Samer Saab Jr, and Asok Ray

Advancing System Performance with Redundancy: 
>From Biological to Artificial Designs
Anh Tuan Nguyen, Jian Xu, Diu Khue Luu, Qi Zhao, and Zhi Yang

A Novel Optimization Framework to Improve the Computational Cost 
of Muscle Activation Prediction for a Neuromusculosketetal System
Seyed Mohammad Ali Rahmati, Mostafa Rostami, and Alireza Karimi

The Information Bottleneck and Geometric Clustering
D. J. Strouse and David J. Schwab


------------

ON-LINE -- http://www.mitpressjournals.org/neuralcomp

MIT Press Journals, One Rogers Street, Cambridge, MA 02142-1209
Tel: (617) 253-2889  FAX: (617) 577-1545 journals-cs at mit.edu

------------