2014 NIPS NeurIPS 2014

Feedforward Learning of Mixture Models

Abstract

We develop a biologically-plausible learning rule that provably converges to the class means of general mixture models. This rule generalizes the classical BCM neural rule within a tensor framework, substantially increasing the generality of the learning problem it solves. It achieves this by incorporating triplets of samples from the mixtures, which provides a novel information processing interpretation to spike-timing-dependent plasticity. We provide both proofs of convergence, and a close fit to experimental data on STDP.

🧭 Keyword Pioneer — tensor method
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning
🌱 Topic Pioneer — Representation Learning
🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
📈 Trend Setter — Self-Supervised Learning