%0 Journal Article
%T How Important is Weight Symmetry in Backpropagation?
%A Qianli Liao
%A Joel Z. Leibo
%A Tomaso Poggio
%J Computer Science
%D 2015
%I arXiv
%X 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.
%U http://arxiv.org/abs/1510.05067v3