This paper studies the convergence properties of the well known K-Means clustering algorithm. The K-Means algorithm can be described either as a gradient descent algorithmor by sl...
We introduce a recurrent architecture having a modular structure and we formulate a training procedure based on the EM algorithm. The resulting model has similarities to hidden Ma...
A new learning algorithmis derived which performs online stochastic gradient ascent in the mutual informationbetween outputs and inputs of a network. In the absence of a priori kn...
In this paper we present results from the first use of neural networks for real-time control of the high temperature plasma in a tokamak fusion experiment. The tokamak is currentl...
Radial Basis Function (RBF) Networks, also known as networks of locally{tuned processing units (see 6]) are well known for their ease of use. Most algorithms used to train these t...
The performance of on-line algorithms for learning dichotomies is studied. In on-line learning, the number of examples P is equivalent to the learning time, since each example is ...
This paper describes the use of a convolutional neural network to perform address block location on machine-printed mail pieces. Locating the address block is a dicult object rec...
While exploring to nd better solutions, an agent performing online reinforcement learning (RL) can perform worse than is acceptable. In some cases, exploration might have unsafe, ...
Satinder P. Singh, Andrew G. Barto, Roderic A. Gru...