How important is weight symmetry in backpropagation?
Gradient backpropagation (BP) requires symmetric feedforward and feedback connections-the same weights must be used for forward and backward passes. This "weight transport problem" (Grossberg 1987) is thought to be one of the main reasons to doubt BP's biologically plausibility. Using...
Main Authors: | Liao, Qianli, Leibo, Joel Z, Poggio, Tomaso A |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
Format: | Article |
Published: |
Association for the Advancement of Artificial Intelligence
2017
|
Online Access: | http://hdl.handle.net/1721.1/112304 https://orcid.org/0000-0003-0076-621X https://orcid.org/0000-0002-3153-916X https://orcid.org/0000-0002-3944-0455 |
Similar Items
-
How Important is Weight Symmetry in Backpropagation?
by: Liao, Qianli, et al.
Published: (2016) -
Unsupervised learning of clutter-resistant visual representations from natural videos
by: Liao, Qianli, et al.
Published: (2015) -
Subtasks of unconstrained face recognition
by: Leibo, Joel Z., et al.
Published: (2016) -
Learning invariant representations and applications to face verification
by: Liao, Qianli, et al.
Published: (2014) -
The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex
by: Leibo, Joel Z, et al.
Published: (2015)