374 search results - page 51 / 75 » Training the random neural network using quasi-Newton method... |
ICONIP
2008
15 years 1 months ago
2008
In this paper, we present the performance of machine learning-based methods for detection of phishing sites. We employ 9 machine learning techniques including AdaBoost, Bagging, S...
189
click to vote
VLDB
2001
ACM
15 years 12 months ago
2001
ACM
Abstract. The optimized distance-based access methods currently available for multidimensional indexing in multimedia databases have been developed based on two major assumptions: ...
106
click to vote
GECCO
2008
Springer
15 years 25 days ago
2008
Springer
Selective sampling is a form of active learning which can reduce the cost of training by only drawing informative data points into the training set. This selected training set is ...
GECCO
2008
Springer
15 years 25 days ago
2008
Springer
A possible alternative to fine topology tuning for Neural Network (NN) optimization is to use Echo State Networks (ESNs), recurrent NNs built upon a large reservoir of sparsely r...
84
Voted
NIPS
2008
15 years 1 months ago
2008
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 ...