NIPS 1996 | Sciweavers

We propose a novelapproach to automaticallygrowing and pruning Hierarchical Mixtures of Experts. The constructive algorithm proposed here enables large hierarchies consisting of s...

Jürgen Fritsch, Michael Finke, Alex Waibel

claim paper

Read More »

10

click to vote

NIPS
1996

133views Information Technology» more NIPS 1996»

Continuous Sigmoidal Belief Networks Trained using Slice Sampling

13 years 5 months ago

Download www.psi.toronto.edu

Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed variables. I propose a simple unit that adds zero-mean G...

Brendan J. Frey

claim paper

Read More »

9

click to vote

NIPS
1996

112views Information Technology» more NIPS 1996»

Neural Network Models of Chemotaxis in the Nematode Caenorhabditis Elegans

13 years 5 months ago

Download chinook.uoregon.edu

Thomas C. Ferrée, Ben A. Marcotte, Shawn R....

claim paper

Read More »

10

click to vote

NIPS
1996

87views Information Technology» more NIPS 1996»

Support Vector Regression Machines

13 years 5 months ago

Download reference.kfupm.edu.sa

Harris Drucker, Christopher J. C. Burges, Linda Ka...

claim paper

Read More »

13

click to vote

NIPS
1996

192views Information Technology» more NIPS 1996»

Multidimensional Triangulation and Interpolation for Reinforcement Learning

13 years 5 months ago

Download www.cs.cmu.edu

Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...

Scott Davies

claim paper

Read More »

13

click to vote

NIPS
1996

110views Information Technology» more NIPS 1996»

Predicting Lifetimes in Dynamically Allocated Memory

13 years 5 months ago

Download www.eecs.umich.edu

Predictions oflifetimesofdynamicallyallocated objects can be used to improve time and space e ciency of dynamic memory management in computer programs. Barrett and Zorn 1993] used...

David A. Cohn, Satinder P. Singh

claim paper

Read More »

14

click to vote

NIPS
1996

202views Information Technology» more NIPS 1996»

Improving the Accuracy and Speed of Support Vector Machines

13 years 5 months ago

Download www.columbia.edu

Support Vector Learning Machines (SVM) are nding application in pattern recognition, regression estimation, and operator inversion for ill-posed problems. Against this very genera...

Christopher J. C. Burges, Bernhard Schölkopf

claim paper

Read More »

7

click to vote

NIPS
1996

107views Information Technology» more NIPS 1996»

Edges are the Independent Components of Natural Scenes

13 years 5 months ago