1343 search results - page 85 / 269 » Learning Weighted Automata |
103
Voted
ML
1998
ACM
15 years 8 days ago
1998
ACM
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
99
Voted
ICRA
2010
IEEE
14 years 11 months ago
2010
IEEE
— This paper addresses the problem of acquiring a hierarchically structured robotic skill in a nonstationary environment. This is achieved through a combination of learning primi...
89
Voted
NIPS
2007
15 years 2 months ago
2007
We propose a compact, low power VLSI network of spiking neurons which can learn to classify complex patterns of mean firing rates on–line and in real–time. The network of int...
101
Voted
CBRMD
2008
15 years 21 days ago
2008
Abstract. This paper describes an approach to detect hints on procurement fraud. It was developed within the context of a European Union project on fraud prevention. Procurement fr...
99
Voted
AAAI
1997
15 years 1 months ago
1997
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...