Higher Structures in Deep Learning
Michael L. Roberts
Carlos Zapata Carratalá Nicholas J. Cooper
Lijun Chen
François G. Meyer
D. Gurari
Computer Science
TL;DR
A novel empirical investigation of higher-arity phenomenon in trained neural networks is conducted, a hypergraphical generalization of the multilayer perceptron is introduced, and connections to evolutionary algorithms are explored.
Abstract
We provide an expository introduction on the importance of higher-arity tensor operations to deep learning. Then, we conduct a novel empirical investigation of higher-arity phenomenon in trained neural networks, introduce a hypergraphical generalization of the multilayer perceptron, and explore connections to evolutionary algorithms. We conclude with a discussion of promising directions for future research.
