An HMM-Based Threshold Model Approach for Gesture Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Spatio-temporal adaptation in the unsupervised development of networked visual neurons
IEEE Transactions on Neural Networks
Principles of Chemical Sensors
Principles of Chemical Sensors
IEEE Transactions on Neural Networks
Pruning recurrent neural networks for improved generalization performance
IEEE Transactions on Neural Networks
ART-EMAP: A neural network architecture for object recognition by evidence accumulation
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
Neurochemical and pharmacological studies of the central nervous system are important in understanding normal brain function and discovering effective treatments for brain diseases. Imaging systems are capable of providing large spatiotemporal chemical information, but they require the subject to remain still during recording. Implantable chemical sensors can be used in freely behaving animals and are able to provide higher resolution than imaging systems, but only in close proximity to the sensor. The aim of this research was to design and evaluate an artificial neural network capable of generating 3D chemical information over time using data acquired from a limited number of chemical sensors that could eventually be recorded from a freely behaving animal. The results show that the spatiotemporal neural network is capable of learning ion diffusion in a model of the cortical brain, in ideal or noisy conditions, and that network simulations of sensor data are as accurate as mathematical simulations.