Learning the Pseudoinverse Solution to Network Weights
This addresses a bottleneck in neuromorphic engineering for synthesizing biologically plausible neural networks, though it is incremental as it builds on existing pseudoinverse frameworks.
The paper tackles the problem of computing pseudoinverses for neural networks, which is not biologically plausible or adaptive, by presenting an online incremental method that is more memory-efficient than traditional singular value decomposition.
The last decade has seen the parallel emergence in computational neuroscience and machine learning of neural network structures which spread the input signal randomly to a higher dimensional space; perform a nonlinear activation; and then solve for a regression or classification output by means of a mathematical pseudoinverse operation. In the field of neuromorphic engineering, these methods are increasingly popular for synthesizing biologically plausible neural networks, but the "learning method" - computation of the pseudoinverse by singular value decomposition - is problematic both for biological plausibility and because it is not an online or an adaptive method. We present an online or incremental method of computing the pseudoinverse, which we argue is biologically plausible as a learning method, and which can be made adaptable for non-stationary data streams. The method is significantly more memory-efficient than the conventional computation of pseudoinverses by singular value decomposition.