From Associative Memories to Deep Networks
About fifty years ago, holography was proposed as a model of associative memory. Associative memories with similar properties were soon after implemented as simple networks of threshold neurons by Willshaw and Longuet-Higgins. In these pages I will show that today’s deep nets are an incremental improvement of the original associative networks. Thinking about deep learning in terms of associative networks provides a more realistic and sober perspective on the promises of deep learning and on its role in eventually understanding human intelligence. As a bonus, this discussion also uncovers connections with several interesting topics in applied math: random features, random projections, neural ensembles, randomized kernels, memory and generalization, vector quantization and hierarchical vector quantization, random vectors and orthogonal basis, NTK and radial kernels.
Center for Brains, Minds and Machines (CBMM)