An error-propagation spiking neural network compatible with neuromorphic processors

• Published in: 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) pp. 84 - 88
• Main Authors: Cartiglia, Matteo, Haessig, Germain, Indiveri, Giacomo
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2020
• Subjects: Biological neural networks; Integrated circuit modeling; Mathematical model; Neuromorphics; Neurons; Training
• DOI: 10.1109/AICAS48895.2020.9073856

Spiking neural networks have shown great promise for the design of low-power sensory-processing and edgecomputing hardware platforms. However, implementing onchip learning algorithms on such architectures is still an open challenge, especially for multi-layer networks that rely on the back-propagation algorithm. In this paper, we present a spikebased learning method that approximates back-propagation using local weight update mechanisms and which is compatible with mixed-signal analog/digital neuromorphic circuits. We introduce a network architecture that enables synaptic weight update mechanisms to back-propagate error signals across layers and present a network that can be trained to distinguish between two spikebased patterns that have identical mean firing rates, but different spike-timings. This work represents a first step towards the design of ultra-low power mixed-signal neuromorphic processing systems with on-chip learning circuits that can be trained to recognize different spatio-temporal patterns of spiking activity (e.g. produced by event-based vision or auditory sensors).