Kernelized Synaptic Weight Matrices

ICML 2018 Lorenz MullerJulien MartelGiacomo Indiveri

In this paper we introduce a novel neural network architecture, in which weight matrices are re-parametrized in terms of low-dimensional vectors, interacting through kernel functions. A layer of our network can be interpreted as introducing a (potentially infinitely wide) linear layer between input and output... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Collaborative Filtering MovieLens 10M Sparse FC RMSE 0.769 # 7
Collaborative Filtering MovieLens 1M Sparse FC RMSE 0.824 # 1