TY - JOUR AU - Frenkel, Charlotte AU - Lefebvre, Martin AU - Bol, David PY - 2021 M3 - Original Research TI - Learning Without Feedback: Fixed Random Learning Signals Allow for Feedforward Training of Deep Neural Networks JO - Frontiers in Neuroscience UR - https://www.frontiersin.org/articles/10.3389/fnins.2021.629892 VL - 15 SN - 1662-453X N2 - While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of low-cost adaptive smart sensors at the edge, as they severely constrain memory accesses and entail buffering overhead. In this work, we show that the one-hot-encoded labels provided in supervised classification problems, denoted as targets, can be viewed as a proxy for the error sign. Therefore, their fixed random projections enable a layerwise feedforward training of the hidden layers, thus solving the weight transport and update locking problems while relaxing the computational and memory requirements. Based on these observations, we propose the direct random target projection (DRTP) algorithm and demonstrate that it provides a tradeoff between accuracy and computational cost that is suitable for adaptive edge computing devices. ER -