Sciweavers

NIPS
1994
13 years 6 months ago
Convergence Properties of the K-Means Algorithms
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...
Léon Bottou, Yoshua Bengio
NIPS
1994
13 years 6 months ago
An Input Output HMM Architecture
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...
Yoshua Bengio, Paolo Frasconi
NIPS
1994
13 years 6 months ago
A Non-linear Information Maximisation Algorithm that Performs Blind Separation
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...
Anthony J. Bell, Terrence J. Sejnowski
NIPS
1994
13 years 6 months ago
Real-Time Control of a Tokamak Plasma Using Neural Networks
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...
Christopher M. Bishop
NIPS
1994
13 years 6 months ago
Boosting the Performance of RBF Networks with Dynamic Decay Adjustment
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...
Michael R. Berthold, Jay Diamond
NIPS
1994
13 years 6 months ago
On-line Learning of Dichotomies
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 ...
N. Barkai, H. Sebastian Seung, Haim Sompolinsky
NIPS
1993
13 years 6 months ago
Postal Address Block Location Using a Convolutional Locator Network
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...
Ralph Wolf, John C. Platt
NIPS
1993
13 years 6 months ago
Robust Reinforcement Learning in Motion Planning
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...