A Stochastic Approach to STDP
This work addresses efficiency for implementing STDP in large-scale spiking neural networks, but it is incremental as it builds on existing digital methods.
The authors tackled the computational expense of exponential decay in STDP learning by proposing a stochastic approach and time multiplexing, achieving 8192 virtual STDP adaptors with one physical implementation and validating it in a balanced excitation/inhibition experiment.
We present a digital implementation of the Spike Timing Dependent Plasticity (STDP) learning rule. The proposed digital implementation consists of an exponential decay generator array and a STDP adaptor array. On the arrival of a pre- and post-synaptic spike, the STDP adaptor will send a digital spike to the decay generator. The decay generator will then generate an exponential decay, which will be used by the STDP adaptor to perform the weight adaption. The exponential decay, which is computational expensive, is efficiently implemented by using a novel stochastic approach, which we analyse and characterise here. We use a time multiplexing approach to achieve 8192 (8k) virtual STDP adaptors and decay generators with only one physical implementation of each. We have validated our stochastic STDP approach with measurement results of a balanced excitation/inhibition experiment. Our stochastic approach is ideal for implementing the STDP learning rule in large-scale spiking neural networks running in real time.