Spike Time Dependent Plasticity (STDP) Learning
Outline:

The current dominating approach to artificial intelligence, deep learning, uses global gradient-based learning, which is demanding in terms of computation time and memory requirements. We implemented a prototype local spike timing dependent plasticity (STDP) learning algorithm that is an alternative or even complementary approach to global learning. We show that this approach scales well, and it can reduce drastically the computational demand of deep learning with many computational layers and with many millions of parameters.

Team members:

  • Miklos Ruszinko
  • Dan Saunders
  • Pegah Taheri
  • Jesse Goodspeed

Illustration of Convolutional Spiking Neural Network with between-patch connectivity
Illustration of Convolutional Spiking Neural Network with between-patch connectivity

Click here for additional details

References