Optimizing One-Shot Learning with Binary Synapses

  title={Optimizing One-Shot Learning with Binary Synapses},
  author={Sandro Romani and Daniel J. Amit and Yali Amit},
  journal={Neural Computation},
A network of excitatory synapses trained with a conservative version of Hebbian learning is used as a model for recognizing the familiarity of thousands of once-seen stimuli from those never seen before. Such networks were initially proposed for modeling memory retrieval (selective delay activity). We show that the same framework allows the incorporation of both familiarity recognition and memory retrieval, and estimate the network's capacity. In the case of binary neurons, we extend the… CONTINUE READING
13 Citations
40 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 13 extracted citations


Publications referenced by this paper.
Showing 1-10 of 40 references

Universal synaptic plasticity mechanism for familiarity and recognition memory

  • D. Amit, V. Yakovlev, S. Romani, S. Hochstein
  • J. Neurosci.,
  • 2008
Highly Influential
7 Excerpts

Multiple working memory model for behavioral experiment

  • D. Amit, A. Bernacchia, V. Yakovlev
  • Cerebral Cortex,
  • 2003
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…