#### Filter Results:

- Full text PDF available (13)

#### Publication Year

1988

2007

- This year (0)
- Last 5 years (0)
- Last 10 years (1)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

- Tal Grossman, Alan S. Lapedes
- NIPS
- 1993

We show how randomly scrambling the output classes of various fractions of the training data may be used to improve predictive accuracy of a classification algorithm. We present a method for calculating the "noise sensitivity signature" of a learning algorithm which is based on scrambling the output classes. This signature can be used to indicate a good… (More)

- Tal Grossman, Ron Meir, Eytan Domany
- NIPS
- 1988

We introduce a learning algorithm for multilayer neural networks composed of binary linear threshold elements. Whereas existing algorithms reduce the learning process to minimizing a cost function over the weights, our method treats the internal representations as the fundamental entities to be determined. Once a correct set of internal representations is… (More)

- Tal Grossman, Robert M. Farber, Alan S. Lapedes
- ISMB
- 1995

Recently, there has been considerable interest in deriving and applying knowledge-based, empirical potential functions for proteins. These empirical potentials have been derived from the statistics of interacting, spatially neighboring residues, as may be obtained from databases of known protein crystal structures. In this paper we employ neural networks to… (More)

- Tal Grossman
- 1993

A neural network model, the INN (Inverted Neurons Network), is applied to the Maximum Clique problem. First, I describe the INN model and how it implements a given graph instance. The model has a threshold parameter t, which determines the character of the network stable states. As shown in an earlier work 5], the stable states of the network correspond to… (More)

- Tal Grossman
- Cliques, Coloring, and Satisfiability
- 1993

- Dimitry Nabutovsky, Tal Grossman, Eytan Domany
- Complex Systems
- 1990

A new learning algorithm for feedforward networks, learning by choice of intern al represent at ions (C HIR), was recently introduced [1,2]. W hereas many algor it hm s red uce th e learning proce ss to minimizing a cost function over t he weights, our method treats th e internal representations as the funda ment al ent it ies to be determi ned. T he algo… (More)

- Tal Grossman
- Complex Systems
- 1989

A new learning algorithm, learning by choice of int ern al repr esentations (CHIR), was recently int roduced. Th e basic version of thi s algoriths was developed for a two-layer, single-out put , feedforward network of binary neurons . This paper presents a generalized version of the CHIR algorithm th at is capable of t raining mult ipleoutput net works. A… (More)

We study the extent to which xing the second layer weights reduces the capacity and generalization ability of a two-layer perceptron. Architectures with N inputs, K hidden units and a single output are considered, with both overlapping and non-overlapping receptive elds. We obtain from simulations one measure of the strength of a network-its critical… (More)

- David H. Wolpert, Emanuel Knill, Tal Grossman
- Statistics and Computing
- 1998

In this paper we analyze the average behavior of the Bayes-optimal and Gibbs learning algorithms. We do this both for oo-training-set error and conventional IID error (for which test sets overlap with training sets). For the IID case we provide a major extension to one of the better known results of 7]. We also show that expected IID test set error is a… (More)

- Harel Z. Shouval, Isaac Shariv, Tal Grossman, Asher A. Friesem, Eytan Domany
- Int. J. Neural Syst.
- 1991