3 accepted papers
Deep neural networks that incorporate classic reinforcement learning methods, such as value iteration, into their structure significantly outperform randomly structured networks in learning and generalization. These networks, however, are mostly limited to environments with no or very low uncertaint…
We present a computationally efficient framework to model a wide range of population structures with high order correlations and a large number of neurons. Our method is based on a special type of Bayesian network that has linear inference time and is founded upon the concept of contextual independe…
To communicate, the ~ 1.5 million Americans living with deafblindess use tactile American Sign Language (t-ASL). To provide Deafßilind (DB) individuals with a means of using their primary communication language without the use of an interpreter, we developed an assistive technology that promotes the…