Author : Elijah Douglas Christensen
Publisher :
ISBN 13 :
Total Pages : 100 pages
Book Rating : 4.:/5 (126 download)
Book Synopsis Deep Artificial Neural Network Models of Neural Encoding in Vision and Neurostimulation by : Elijah Douglas Christensen
Download or read book Deep Artificial Neural Network Models of Neural Encoding in Vision and Neurostimulation written by Elijah Douglas Christensen and published by . This book was released on 2018 with total page 100 pages. Available in PDF, EPUB and Kindle. Book excerpt: There is a significant need for more effective treatments for neurological and psychiatric diseases. Implantable neurostimulators are increasingly used as new therapeutic options for these diseases. This work will discuss our approach to mitigate current limitations in two types of implantable neurostimulators: Deep brain stimulation in treating Parkinson's disease and cortical prosthetics in vision. Deep brain stimulators (DBS) are typically configured to deliver therapeutic stimulation constantly, which can produce unavoidable side-effects and needlessly drains power. Modulating stimulation adaptively, or closed-loop stimulation, could mitigate these issues but requires methods to accurately read physiologically relevant brain states, preferably using only the already implanted electrodes. Another class of implanted neurostimulators, cortical prosthetics, rely on accurate predictions of neural activity in the targeted brain area for arbitrary stimuli. Current models used to predict neural activity in primary visual cortex only achieve 35% predictability overall and predictability declines in subsequent areas of visual processing. With a focus on DBS and cortical prosthetics, we highlight how deep artificial neural network (ANN) models can be leveraged as a tool in neuroscience for studying neural encoding and decoding. We apply an ANN model trained using supervised learning to decode sleep state continuously from "spectral fingerprints" contained in local field potential activity of DBS electrodes. Furthermore, we show that deep convolutional neural networks can be used to make more accurate predictions of cortical neural encoding of visual stimuli in both early (primary visual cortex) and late (inferior temporal cortex) stages of visual processing.