Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
A system for musical accompaniment is presented in which a computer-driven orchestra follows and learns from a soloist in a concerto-like setting. The system is decomposed into th...
For many supervised learning tasks it may be infeasible (or very expensive) to obtain objective and reliable labels. Instead, we can collect subjective (possibly noisy) labels fro...
Vikas C. Raykar, Shipeng Yu, Linda H. Zhao, Gerard...
We investigate incremental word learning with few training examples in a Hidden Markov Model (HMM) framework suitable for an interactive learning scenario with little prior knowle...
Abstract-- Extending traditional models for discriminative labeling of structured data to include higher-order structure in the labels results in an undesirable exponential increas...