Sciweavers

NIPS
2000
14 years 26 days ago
Analysis of Bit Error Probability of Direct-Sequence CDMA Multiuser Demodulators
We analyze the bit error probability of multiuser demodulators for directsequence binary phase-shift-keying (DS/BPSK) CDMA channel with additive gaussian noise. The problem of mul...
Toshiyuki Tanaka
NIPS
2000
14 years 26 days ago
Kernel Expansions with Unlabeled Examples
Modern classification applications necessitate supplementing the few available labeled examples with unlabeled examples to improve classification performance. We present a new tra...
Martin Szummer, Tommi Jaakkola
NIPS
2000
14 years 26 days ago
APRICODD: Approximate Policy Construction Using Decision Diagrams
We propose a method of approximate dynamic programming for Markov decision processes (MDPs) using algebraic decision diagrams (ADDs). We produce near-optimal value functions and p...
Robert St-Aubin, Jesse Hoey, Craig Boutilier
NIPS
2000
14 years 26 days ago
The Early Word Catches the Weights
Mark A. Smith, Garrison W. Cottrell, Karen L. Ande...
NIPS
2000
14 years 26 days ago
Development of Hybrid Systems: Interfacing a Silicon Neuron to a Leech Heart Interneuron
We have developed a silicon neuron that is inspired by a mathematical model of the leech heartbeat (HN) interneuron. The temporal and ionic current behaviors of this silicon neuro...
Mario F. Simoni, Gennady S. Cymbalyuk, Michael E. ...
NIPS
2000
14 years 26 days ago
Balancing Multiple Sources of Reward in Reinforcement Learning
For many problems which would be natural for reinforcement learning, the reward signal is not a single scalar value but has multiple scalar components. Examples of such problems i...
Christian R. Shelton
NIPS
2000
14 years 26 days ago
An Information Maximization Approach to Overcomplete and Recurrent Representations
The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model consists of a network of input units driving...
Oren Shriki, Haim Sompolinsky, Daniel D. Lee
NIPS
2000
14 years 26 days ago
The Kernel Trick for Distances
A method is described which, like the kernel trick in support vector machines (SVMs), lets us generalize distance-based algorithms to operate in feature spaces, usually nonlinearl...
Bernhard Schölkopf