Sciweavers

4080 search results - page 615 / 816
» The rebirth of neural networks
Sort
View
ICPR
2008
IEEE
16 years 1 months ago
A supervised learning approach for imbalanced data sets
This paper presents a new learning approach for pattern classification applications involving imbalanced data sets. In this approach, a clustering technique is employed to resamp...
Giang Hoang Nguyen, Abdesselam Bouzerdoum, Son Lam...
IJCNN
2008
IEEE
16 years 1 months ago
Long-term prediction of time series using NNE-based projection and OP-ELM
Abstract— This paper proposes a combination of methodologies based on a recent development –called Extreme Learning Machine (ELM)– decreasing drastically the training time of...
Antti Sorjamaa, Yoan Miche, Robert Weiss, Amaury L...
FOCI
2007
IEEE
16 years 28 days ago
Opposite Transfer Functions and Backpropagation Through Time
— Backpropagation through time is a very popular discrete-time recurrent neural network training algorithm. However, the computational time associated with the learning process t...
Mario Ventresca, Hamid R. Tizhoosh
ICC
2007
IEEE
133views Communications» more  ICC 2007»
16 years 27 days ago
Machine Learning for Automatic Defence Against Distributed Denial of Service Attacks
— Distributed Denial of Service attacks pose a serious threat to many businesses which rely on constant availability of their network services. Companies like Google, Yahoo and A...
Stefan Seufert, Darragh O'Brien
ICC
2007
IEEE
148views Communications» more  ICC 2007»
16 years 27 days ago
Improved Revenue and Radio Resource Usage through Inter-Operator Joint Radio Resource Management
— This paper proposes a two-layer Joint Radio Resource Management (JRRM) framework to improve the efficiency in multi-radio and multi-operator cellular scenarios. On the one hand...
Lorenza Giupponi, Ramón Agustí, Jord...