VLDB 2026 Research / reviewers in the wild / expert
Tal Grossman
dblp:51/4113
· DBLP profile ↗
7ranked-venue papers
5as first author
0since 2021 · last 1995
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 6 · 4 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-authorApplied, interdisciplinary, general and emerging computing · 1 · 1 first-author
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
3 papers |
Deep learning architectures and training · 61% Trustworthy machine learning · 39% | |
| Interdisciplinary, comprehensive, and emerging computing
1 paper |
Bioinformatics and computational biology · 100% |
Topics — the 4 heaviest of 6, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Bioinformatics and computational biology
protein structure prediction |
0.0 | 1 | 1995 | Neural Net Representations of Empirical Protein Potentials · ISMB 1995 |
Machine learning › Trustworthy machine learning › robustness › noisy data
noisy training data |
0.0 | 1 | 1993 | Use of Bad Training Data for Better Predictions · NIPS 1993 |
Machine learning › Deep learning architectures and training › data-centric deep learning
training data quality |
0.0 | 1 | 1993 | Use of Bad Training Data for Better Predictions · NIPS 1993 |
Machine learning › Deep learning architectures and training
feedforward neural network |
0.0 | 1 | 1989 | The CHIR Algorithm for Feed Forward Networks with Binary Weights · NIPS 1989 |
Methods — techniques the papers use, named apart from their topics
neural network · 0.0CHIR algorithm · 0.0
| Year | Publication | Venue | Position |
|---|---|---|---|
| 1995 | Neural Net Representations of Empirical Protein Potentials
Tal Grossman, Robert M. Farber, Alan S. Lapedes |
ISMB | 1 |
| 1994 | Noise sensitivity signatures for model selectionabstractPresents a method for calculating the "noise sensitivity signature" of a learning algorithm which is based on scrambling the output classes of various fractions of the training data. This signature can be used to indicate a good (or bad) match between the complexity of the classifier and the complexity of the data and hence to improve the predictive accuracy of a classification algorithm. Use of noise sensitivity signatures is distinctly different from other schemes to avoid overtraining, such as cross-validation, which uses only part of the training data, or various penalty functions, which are not data-adaptive. Noise sensitivity signature methods use all of the training data and are manifestly data-adaptive and nonparametric. They are well suited for situations with limited training data. Tal Grossman, Alan S. Lapedes |
ICPR (2) | 1 |
| 1993 | Use of Bad Training Data for Better Predictions
Tal Grossman, Alan S. Lapedes |
NIPS | 1 |
| 1993 | A Neural Network Classifier In Experimental Particle PhysicsabstractA classification problem in high energy physics has been solved on simulated data using a simple multilayer perceptron comprising binary units which was trained with the CHIR algorithm. The unstable training of such a network on a nonseparable set has been overcome by selecting those weight vectors with good performance while providing a flexible choice of the two types of classification errors. Specific features of the problem have been exploited in order to simplify and optimize the solution which has been compared to the popular backpropagation algorithm and found to perform on a similar level. Additional aspects of this work are the use of the CHIR algorithm on continuous input and incorporating the classic idea of a phi-machine in a multilayer perceptron. Amir A. Handzel, Tal Grossman, Eytan Domany, Shlomit Tarem, Ehud Duchovni |
Int. J. Neural Syst. | 2 |
| 1991 | An All-Optical Hopfield Network: Theory and ExperimentabstractThe implementation of an all-optical Hopfield-type neural network is made possible by eliminating the need for subtracting light intensities. This implementation is achieved without significantly degrading the network's performance, when only inhibitory connections (i.e., Jij <0) are used. The theoretical analysis of such a network, and its experimental implementation, exploiting a liquid crystal light valve for the neurons and an array of subholograms for the interconnections, are presented. Harel Z. Shouval, Isaac Shariv, Tal Grossman, Asher A. Friesem, Eytan Domany |
Int. J. Neural Syst. | 3 |
| 1989 | The CHIR Algorithm for Feed Forward Networks with Binary Weights
Tal Grossman |
NIPS | 1 |
| 1988 | Learning by Choice of Internal Representations
Tal Grossman, Ron Meir, Eytan Domany |
NIPS | 1 |