KIP-Veröffentlichungen

Jahr 2019
Autor(en) Timo C. Wunderlich, Akos F. Kungl, Eric Müller, Johannes Schemmel, Mihai Petrovici
Titel Brain-Inspired Hardware for Artificial Intelligence: Accelerated Learning in a Physical-Model Spiking Neural Network
KIP-Nummer HD-KIP 19-77
KIP-Gruppe(n) F9
Dokumentart Paper
Keywords (angezeigt) Neuromorphic computing, Spiking networks, Plasticity
Quelle Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation (2019)
doi 10.1007/978-3-030-30487-4_10
Abstract (en)

Future developments in artificial intelligence will profit from the existence of novel, non-traditional substrates for brain-inspired computing. Neuromorphic computers aim to provide such a substrate that reproduces the brain’s capabilities in terms of adaptive, low-power information processing. We present results from a prototype chip of the BrainScaleS-2 mixed-signal neuromorphic system that adopts a physical-model approach with a 1000-fold acceleration of spiking neural network dynamics relative to biological real time. Using the embedded plasticity processor, we both simulate the Pong arcade video game and implement a local plasticity rule that enables reinforcement learning, allowing the on-chip neural network to learn to play the game. The experiment demonstrates key aspects of the employed approach, such as accelerated and flexible learning, high energy efficiency and resilience to noise.

bibtex
@article{wunderlich2019,
  author   = {Wunderlich T.C., Kungl A.F., Müller E., Schemmel J., Petrovici M.},
  title    = {Brain-Inspired Hardware for Artificial Intelligence: Accelerated Learning in a Physical-Model Spiking Neural Network},
  journal  = {Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation},
  year     = {2019},
  volume   = {},
  pages    = {119-122},
  doi      = {10.1007/978-3-030-30487-4_10},
  url      = {https://link.springer.com/chapter/10.1007/978-3-030-30487-4_10}
}
URL Springer Link
Datei Poster
URL arXiV
KIP - Bibliothek
Im Neuenheimer Feld 227
Raum 3.402
69120 Heidelberg