Title :
Neuromorphic adaptations of restricted Boltzmann machines and deep belief networks
Author :
Pedroni, Bruno U. ; Das, S. ; Neftci, Emre ; Kreutz-Delgado, Kenneth ; Cauwenberghs, Gert
Author_Institution :
Bioeng. Dept., Univ. of California, San Diego, La Jolla, CA, USA
Abstract :
Restricted Boltzmann Machines (RBMs) and Deep Belief Networks (DBNs) have been demonstrated to perform efficiently on a variety of applications, such as dimensionality reduction and classification. Implementation of RBMs on neuromorphic platforms, which emulate large-scale networks of spiking neurons, has significant advantages from concurrency and low-power perspectives. This work outlines a neuromorphic adaptation of the RBM, which uses a recently proposed neural sampling algorithm (Buesing et al. 2011), and examines its algorithmic efficiency. Results show the feasibility of such alterations, which will serve as a guide for future implementation of such algorithms in neuromorphic very large scale integration (VLSI) platforms.
Keywords :
Boltzmann machines; belief networks; sampling methods; DBN; RBM; deep belief networks; dimensionality reduction; large-scale spiking neuron networks; neural sampling algorithm; neuromorphic VLSI platforms; neuromorphic adaptations; neuromorphic platforms; neuromorphic very large scale integration platforms; restricted Boltzmann machines; Accuracy; Bayes methods; Hardware; Machine learning algorithms; Neuromorphics; Neurons; Training;
Conference_Titel :
Neural Networks (IJCNN), The 2013 International Joint Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4673-6128-6
DOI :
10.1109/IJCNN.2013.6707067