DeepAI AI Chat
Log In Sign Up

Spatiotemporal Information Processing with a Reservoir Decision-making Network

by   Yuanyuan Mi, et al.
Peking University
NetEase, Inc

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.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8


Self-Evolutionary Reservoir Computer Based on Kuramoto Model

The human brain's synapses have remarkable activity-dependent plasticity...

Local reservoir model for choice-based learning

Decision making based on behavioral and neural observations of living sy...

V2V Spatiotemporal Interactive Pattern Recognition and Risk Analysis in Lane Changes

In complex lane change (LC) scenarios, semantic interpretation and safet...

Space-Time Domain Tensor Neural Networks: An Application on Human Pose Recognition

Recent advances in sensing technologies require the design and developme...

Modeling Traffic Congestion with Spatiotemporal Big Data for An Intelligent Freeway Monitoring System

Traffic congestion is a complex, nonlinear spatiotemporal modeling probl...

Learning What and Where – Unsupervised Disentangling Location and Identity Tracking

Our brain can almost effortlessly decompose visual data streams into bac...