Initial specifications

Up to Neural network architecture and design
Initial specifications to kick off the discussion

Neural network algorithms and types

Posted by Giacomo Indiveri at February 27. 2015

Here are some properties of the neural networks that I propose as a staring point for our discussions and project definition:

  1. Spiking: we will investigate spiking neural network (as opposed to graded or analog)
  2. Configurable: we will aim for a flexible implementation that will allow us to explore different network topologies, including recurrent, multi-layer, convolutional, deep, etc.
  3. Dynamic synapses: the synapses will not be a simple multiplier, but will have complex dynamics and tunable non-linear characteristics, and tunable time constants
  4. Limited resolution: the algorithms will have to work with limited resolution synaptic weights (i.e. the synapses will produce analog continuous currents but multiplied by weight values that can take only a small number of bits).
  5. Real-time dynamics: both synapses and neurons will have the possibility of using biologically plausible time constants, for use cases that require real-time interaction with the environment (e.g. understanding an auditory scene in real-time).
  6. Possibility to speed-up computation: the synapses and neurons will allow the possibility to run faster than real-time (at the price of higher power consumption)
  7. Learning versus no-learning: as a short-term goal (to minimize risk) we will tackle problems that can be solved with off-line learning paradigms that down-load the weights to the VLSI device once the weights have been learned. As a long-term goal however we should include learning in the loop, and include the possibility to implement in-situ on-line learning.
Powered by Ploneboard