Neural networks with motivation

no code implementations • 23 Jun 2019 • Sergey A. Shuvaev, Ngoc B. Tran, Marcus Stephenson-Jones, Bo Li, Alexei A. Koulakov

First, we show that Q-learning neural networks with motivation can navigate in environment with dynamic rewards.

Hierarchical Reinforcement Learning Navigate +3

Representations of Sound in Deep Learning of Audio Features from Music

no code implementations • 8 Dec 2017 • Sergey Shuvaev, Hamza Giaffar, Alexei A. Koulakov

Yet, there is often a discernable character to the work of, for instance, individual composers at the perceptual level - an experienced listener can often pick up on subtle clues in the music to identify the composer or performer.

Audio Classification General Classification