In this paper we aim to train deep neural networks for rapid visual recognition. The task is highly challenging, largely due to the lack of a meaningful regularizer on the functio...
We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifier...
Prediction of dynamic features is an important task for determining the manipulation strategies of an object. This paper presents a technique for predicting dynamics of objects re...
Shun Nishide, Tetsuya Ogata, Jun Tani, Kazunori Ko...
A recurrent neural network can possess multiple stable states, a property that many brain theories have implicated in learning and memory. There is good evidence for such multista...
As postgenomic biology becomes more predictive, the ability to infer rate parameters of genetic and biochemical networks will become increasingly important. In this paper, we expl...