Emergent Bio-Functional Similarities in a Cortical-Spike-Train-Decoding Spiking Neural Network Facilitate Predictions of Neural Computation
This work addresses the challenge of building biologically authentic models for neural computation, particularly in neuroscience applications, though it appears incremental as it builds on existing SNN approaches with specific topological and functional enhancements.
The study tackled the problem of low performance and limited biological realism in spiking neural networks (SNNs) for classifying biological spike trains by proposing motorSRNN, a recurrent SNN inspired by primate motor circuits, which achieved a good balance between classification accuracy and energy consumption while demonstrating bio-functional similarities like cosine-tuning observed in monkeys.
Despite its better bio-plausibility, goal-driven spiking neural network (SNN) has not achieved applicable performance for classifying biological spike trains, and showed little bio-functional similarities compared to traditional artificial neural networks. In this study, we proposed the motorSRNN, a recurrent SNN topologically inspired by the neural motor circuit of primates. By employing the motorSRNN in decoding spike trains from the primary motor cortex of monkeys, we achieved a good balance between classification accuracy and energy consumption. The motorSRNN communicated with the input by capturing and cultivating more cosine-tuning, an essential property of neurons in the motor cortex, and maintained its stability during training. Such training-induced cultivation and persistency of cosine-tuning was also observed in our monkeys. Moreover, the motorSRNN produced additional bio-functional similarities at the single-neuron, population, and circuit levels, demonstrating biological authenticity. Thereby, ablation studies on motorSRNN have suggested long-term stable feedback synapses contribute to the training-induced cultivation in the motor cortex. Besides these novel findings and predictions, we offer a new framework for building authentic models of neural computation.