How Important is Weight Symmetry in Backpropagation?
Name
CBMM-Memo-036.pdf
Size
615.32 KB
Format
Adobe PDF
Checksum (MD5)
5e5092f7dd8efb85c2f1ddc18d2bbcb5
Author(s)
Liao, Qianli
Leibo, Joel Z.
Poggio, Tomaso
Date Issued
November 29, 2015
Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1510.05067v3
Series/Report no.
CBMM Memo Series;036
Abstract
Gradient backpropagation (BP) requires symmetric feedforward and feedback connections—the same weights must be used for forward and backward passes. This “weight transport problem” [1] is thought to be one of the main reasons of BP’s biological implausibility. Using 15 different classification datasets, we systematically study to what extent BP really depends on weight symmetry. In a study that turned out to be surprisingly similar in spirit to Lillicrap et al.’s demonstration [2] but orthogonal in its results, our experiments indicate that: (1) the magnitudes of feedback weights do not matter to performance (2) the signs of feedback weights do matter—the more concordant signs between feedforward and their corresponding feedback connections, the better (3) with feedback weights having random magnitudes and 100% concordant signs, we were able to achieve the same or even better performance than SGD. (4) some normalizations/stabilizations are indispensable for such asymmetric BP to work, namely Batch Normalization (BN) [3] and/or a “Batch Manhattan” (BM) update rule.
Subjects
Gradient backpropagation (BP)
Batch Normalization (BN)
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
