Sciweavers

2924 search results - page 364 / 585
» On the Use of Evidence in Neural Networks
Sort
View
172
Voted
HICSS
2003
IEEE
220views Biometrics» more  HICSS 2003»
15 years 12 months ago
Applications of Hidden Markov Models to Detecting Multi-Stage Network Attacks
This paper describes a novel approach using Hidden Markov Models (HMM) to detect complex Internet attacks. These attacks consist of several steps that may occur over an extended pe...
Dirk Ourston, Sara Matzner, William Stump, Bryan H...
KDD
2004
ACM
150views Data Mining» more  KDD 2004»
16 years 7 months ago
Complete This Puzzle: A Connectionist Approach to Accurate Web Recommendations Based on a Committee of Predictors
Abstract. We present a Context Ultra-Sensitive Approach based on two-step Recommender systems (CUSA-2step-Rec). Our approach relies on a committee of profile-specific neural networ...
Olfa Nasraoui, Mrudula Pavuluri
GECCO
2007
Springer
201views Optimization» more  GECCO 2007»
16 years 23 days ago
Evolving explicit opponent models in game playing
Opponent models are necessary in games where the game state is only partially known to the player, since the player must infer the state of the game based on the opponent’s acti...
Alan J. Lockett, Charles L. Chen, Risto Miikkulain...
NIPS
2008
15 years 8 months ago
On Computational Power and the Order-Chaos Phase Transition in Reservoir Computing
Randomly connected recurrent neural circuits have proven to be very powerful models for online computations when a trained memoryless readout function is appended. Such Reservoir ...
Benjamin Schrauwen, Lars Buesing, Robert A. Legens...
BC
2002
90views more  BC 2002»
15 years 6 months ago
What can the hippocampal representation of environmental geometry tell us about Hebbian learning?
The importance of the hippocampus in spatial representation is well established. It is suggested that the rodent hippocampal network should provide an optimal substrate for the stu...
Colin Lever, Neil Burgess, Francesca Cacucci, Tom ...