Sciweavers

NIPS
1996
14 years 26 days ago
Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation
In pattern recognition, statistical modeling, or regression, the amount of data is a critical factor affecting the performance. If the amount of data and computational resources ar...
Patrice Simard, Yann LeCun, John S. Denker, Bernar...
NIPS
1996
14 years 26 days ago
Monotonicity Hints
: Neural networks are competitive tools for classification problems. In this context, a hint is any piece of prior side information about the classification. Common examples are mo...
Joseph Sill, Yaser S. Abu-Mostafa
NIPS
1996
14 years 26 days ago
Exploiting Model Uncertainty Estimates for Safe Dynamic Control Learning
Model learning combined with dynamic programming has been shown to be e ective for learning control of continuous state dynamic systems. The simplest method assumes the learned mod...
Jeff G. Schneider
NIPS
1996
14 years 26 days ago
Second-order Learning Algorithm with Squared Penalty Term
This paper compares three penalty terms with respect to the efficiency of supervised learning, by using first- and second-order learning algorithms. Our experiments showed that fo...
Kazumi Saito, Ryohei Nakano
NIPS
1996
14 years 26 days ago
Neural Models for Part-Whole Hierarchies
We present a connectionist method for representing images that explicitlyaddresses their hierarchicalnature. It blends data fromneuroscience about whole-object viewpoint sensitive...
Maximilian Riesenhuber, Peter Dayan
NIPS
1996
14 years 26 days ago
Early Stopping-But When?
Abstract. Validation can be used to detect when over tting starts during supervised training of a neural network; training is then stopped before convergence to avoid the over ttin...
Lutz Prechelt
NIPS
1996
14 years 26 days ago
Why did TD-Gammon Work?
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference learning for other applications or ...
Jordan B. Pollack, Alan D. Blair
NIPS
1996
14 years 26 days ago
Maximum Likelihood Blind Source Separation: A Context-Sensitive Generalization of ICA
In the square linear blind source separation problem, one must nd a linear unmixing operator which can detangle the result xi(t) of mixing n unknown independent sources si(t) thro...
Barak A. Pearlmutter, Lucas C. Parra
NIPS
1996
14 years 26 days ago
Are Hopfield Networks Faster than Conventional Computers?
It is shown that conventional computers can be exponentially faster than planar Hopfield networks: although there are planar Hopfield networks that take exponential time to conver...
Ian Parberry, Hung-Li Tseng