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...
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
— High-order human cognition involves processing of abstract and categorically represented knowledge. Traditionally, it has been considered that there is a single innate internal...
Abstract— Cognitive control - the ability to produce appropriate behavior in complex situations - is a fundamental aspect of intelligence. It is increasingly evident that this co...
The Expectation Maximization (EM) algorithm is widely used for learning finite mixture models despite its greedy nature. Most popular model-based clustering techniques might yield...
Chandan K. Reddy, Hsiao-Dong Chiang, Bala Rajaratn...