Spatiotemporal Information Processing with a Reservoir Decision-making Network
This work addresses spatiotemporal information processing in neuroscience, offering insights for brain-inspired algorithms, but it appears incremental as it builds on existing neural network models.
The study tackled spatiotemporal pattern recognition by proposing a reservoir decision-making network, which successfully reproduced looming pattern recognition and learned to discriminate gait with very few training examples.
Spatiotemporal information processing is fundamental to brain functions. The present study investigates a canonic neural network model for spatiotemporal pattern recognition. Specifically, the model consists of two modules, a reservoir subnetwork and a decision-making subnetwork. The former projects complex spatiotemporal patterns into spatially separated neural representations, and the latter reads out these neural representations via integrating information over time; the two modules are combined together via supervised-learning using known examples. We elucidate the working mechanism of the model and demonstrate its feasibility for discriminating complex spatiotemporal patterns. Our model reproduces the phenomenon of recognizing looming patterns in the neural system, and can learn to discriminate gait with very few training examples. We hope this study gives us insight into understanding how spatiotemporal information is processed in the brain and helps us to develop brain-inspired application algorithms.