NIPS
1994
13 years 5 months ago
1994
NIPS
1994
13 years 5 months ago
1994
For many types of machine learning algorithms, one can compute the statistically optimal" way to select training data. In this paper, we review how optimal data selection tec...
NIPS
1994
13 years 5 months ago
1994
The spatial distribution and time course of electrical signals in neurons have important theoretical and practical consequences. Because it is difficult to infer how neuronal form...
NIPS
1994
13 years 5 months ago
1994
Biological sensorimotor systems are not static maps that transform input sensory information into output motor behavior. Evidence from many lines of research suggests that their r...
NIPS
1994
13 years 5 months ago
1994
To appear in: G. Tesauro, D. S. Touretzky and T. K. Leen, eds., Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, 1995. A straightforward approach to t...
NIPS
1994
13 years 5 months ago
1994
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...
NIPS
1994
13 years 5 months ago
1994
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...
NIPS
1994
13 years 5 months ago
1994
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...
NIPS
1994
13 years 5 months ago
1994
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...
NIPS
1994
13 years 5 months ago
1994
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...