A learning scheme replacing a transposed forward-weight matrix in the teaching signal with a separate fixed random matrix. Simulations show that adaptation of the forward weights can make this feedback useful on tested tasks. It need not equal the exact loss gradient, and successful simulations alone do not establish the mechanism in the brain.[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
Articles by others on the same topic
There are currently no matching articles.