Biologically-Plausible Learning Algorithms Can Scale to Large Datasets

Biologically-Plausible Learning Algorithms Can Scale to Large Datasets

Show other versions (1)

The backpropagation (BP) algorithm is often thought to be biologically implausible in the brain. One of the main reasons is that BP requires symmetric weight matrices in the feedforward and feed- back pathways. To address this “weight transport problem” (Grossberg, 1987), two more biologically plaus...

Full description

Bibliographic Details
Main Authors: Xiao, Will, Chen, Honglin, Liao, Qianli, Poggio, Tomaso
Format: Technical Report
Language:en_US
Published: Center for Brains, Minds and Machines (CBMM) 2018
Subjects:
backpropagation
feedback alignment
sign-symmetry algorithm
Online Access:http://hdl.handle.net/1721.1/118195

Internet

http://hdl.handle.net/1721.1/118195

Similar Items