Synchronized stepwise control of firing and learning thresholds in a spiking randomly connected neural network toward hardware implementation

• DOI: 10.3389/fnins.2024.1402646
• Publication Date: 2024-11-13T11:51:11Z
• Authors: Kumiko Nomura; Yoshifumi Nishi
• Keywords: FOS: Computer and information sciences; 0301 basic medicine; synaptic plasticity; randomly connected neural network; Computer Science - Neural and Evolutionary Computing; Neurosciences. Biological psychiatry. Neuropsychiatry; neuromorphic chip; spiking neural network; intrinsic plasticity; 03 medical and health sciences; Neural and Evolutionary Computing (cs.NE); RC321-571; Neuroscience

Spiking randomly connected neural network (RNN) hardware is promising as ultimately low power devices for temporal data processing at the edge. Although potential of RNNs has been demonstrated, randomness architecture often causes performance degradation. To mitigate such degradation, self-organization mechanism using intrinsic plasticity (IP) and synaptic (SP) should be implemented in spiking RNN. Therefore, we propose hardware-oriented models these functions. implement function IP, a variable firing threshold introduced to each excitatory neuron RNN that changes stepwise accordance with its activity. We also define other thresholds SP synchronize threshold, which determine direction update executed on receiving pre-synaptic spike. discuss effectiveness our model, perform simulations learning anomaly detection publicly available electrocardiograms (ECGs) observe IP realizes true positive rate 1 false being suppressed 0 successfully, does not occur otherwise. Furthermore, find well weights can reduced binary if appropriately designed. This contributes minimization circuit neuronal system having SP.