Deep Neural Networks in Computational Neuroscience
- 25 January 2019
- reference entry
- Published by Oxford University Press (OUP)
Abstract
The goal of computational neuroscience is to find mechanistic explanations of how the nervous system processes information to give rise to cognitive function and behavior. At the heart of the field are its models, that is, mathematical and computational descriptions of the system being studied, which map sensory stimuli to neural responses and/or neural to behavioral responses. These models range from simple to complex. Recently, deep neural networks (DNNs) have come to dominate several domains of artificial intelligence (AI). As the term “neural network” suggests, these models are inspired by biological brains. However, current DNNs neglect many details of biological neural networks. These simplifications contribute to their computational efficiency, enabling them to perform complex feats of intelligence, ranging from perceptual (e.g., visual object and auditory speech recognition) to cognitive tasks (e.g., machine translation), and on to motor control (e.g., playing computer games or controlling a robot arm). In addition to their ability to model complex intelligent behaviors, DNNs excel at predicting neural responses to novel sensory stimuli with accuracies well beyond any other currently available model type. DNNs can have millions of parameters, which are required to capture the domain knowledge needed for successful task performance. Contrary to the intuition that this renders them into impenetrable black boxes, the computational properties of the network units are the result of four directly manipulable elements: input statistics, network structure, functional objective, and learning algorithm. With full access to the activity and connectivity of all units, advanced visualization techniques, and analytic tools to map network representations to neural data, DNNs represent a powerful framework for building task-performing models and will drive substantial insights in computational neuroscience.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- What are the Visual Features Underlying Human Versus Machine Vision?2017
- Deep Residual Learning for Image Recognition2016
- Difference Target Propagation2015
- Recurrent convolutional neural network for object recognition2015
- Deeply learned face representations are sparse, selective, and robust2015
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- Visualizing and Understanding Convolutional Networks2014
- Deep auto-encoder neural networks in reinforcement learning2010
- Invariant Object Recognition with Slow Feature Analysis2008