IEEE - Institute of Electrical and Electronics Engineers, Inc. - Scalable energy-efficient, low-latency implementations of trained spiking Deep Belief Networks on SpiNNaker

2015 International Joint Conference on Neural Networks (IJCNN)

Author(s): Evangelos Stromatias ; Daniel Neil ; Francesco Galluppi ; Michael Pfeiffer ; Shih-Chii Liu ; Steve Furber
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 July 2015
Conference Location: Killarney, Ireland
Conference Date: 12 July 2015
Page(s): 1 - 8
ISBN (Electronic): 978-1-4799-1960-4
ISBN (DVD): 978-1-4799-1959-8
ISSN (Electronic): 2161-4407
DOI: 10.1109/IJCNN.2015.7280625
Regular:

Deep neural networks have become the state-of-the-art approach for classification in machine learning, and Deep Belief Networks (DBNs) are one of its most successful representatives. DBNs consist... View More

Advertisement