Weight transport problem
ID: weight-transport-problem
Exact backpropagation computes hidden teaching signals using the transpose of the current forward weight matrix. Explaining how a biological feedback pathway could know or maintain those weights is the weight transport problem. Useful approximate error correction need not satisfy exact reciprocal weight equality.[ref]
Random synaptic feedback weights support error backpropagation for deep learning by Timothy P. Lillicrap and others. Results, Figure 1 and Figure 2; Discussion: random feedback, learning performance and biological limitations
New to topics? Read the docs here!