Neuromorphic adaptations of restricted Boltzmann machines and deep belief networks

Bruno U. Pedroni, Srinjoy Das, Emre Neftci, Kenneth Kreutz-Delgado, Gert CauwenberghsIJCNN 2013 · OpenReview

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.
BibTeX
@inproceedings{pedroni2013neuromorphic,
  author = {Bruno U. Pedroni and Srinjoy Das and Emre Neftci and Kenneth Kreutz-Delgado and Gert Cauwenberghs},
  title = {{Neuromorphic adaptations of restricted Boltzmann machines and deep belief networks}},
  booktitle = {IJCNN},
  year = {2013},
  url = {https://openreview.net/forum?id=jX4cEepjmo},
}

Loading related content...

Figure