A mixed-signal implementation of a polychronous spiking neural network with delay adaptation

Abstract

Read online

We present a mixed-signal implementation of a re-configurable polychronous spiking neural network capable of storing and recalling spatio-temporal patterns. The proposed neural network contains one neuron array and one axon array. Spike Timing Dependent Delay Plasticity is used to fine-tune delays and add dynamics to the network. In our mixed-signal implementation, the neurons and axons have been implemented as both analogue and digital circuits. The system thus consists of one FPGA, containing the digital neuron array and the digital axon array, and one analogue IC containing the analogue neuron array and the analogue axon array. The system can be easily configured to use different combinations of each. We present and discuss the experimental results of all combinations of the analogue and digital axon arrays and the analogue and digital neuron arrays. The test results show that the proposed neural network is capable of successfully recalling more than 85% of stored patterns using both analogue and digital circuits.

Keywords

• neuromorphic engineering
• polychronous spiking neural network
• multiplexed neuron array
• mixed-signal implementation
• analogue implementation