The Roles of Supervised Machine Learning in Systems Neuroscience
arXiv:1805.08239
Abstract
Over the last several years, the use of machine learning (ML) in neuroscience has been rapidly increasing. Here, we review ML's contributions, both realized and potential, across several areas of systems neuroscience. We describe four primary roles of ML within neuroscience: 1) creating solutions to engineering problems, 2) identifying predictive variables, 3) setting benchmarks for simple models of the brain, and 4) serving itself as a model for the brain. The breadth and ease of its applicability suggests that machine learning should be in the toolbox of most systems neuroscientists.
References in corpus (12)
- Scikit-learn: Machine Learning in Python
- A Survey on Deep Learning in Medical Image Analysis
- Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learning
- Supervised Learning in Spiking Neural Networks with FORCE Training
- On the importance of single directions for generalization
- Emergence of grid-like representations by training recurrent neural networks to perform spatial localization
- Deep Learning Models of the Retinal Response to Natural Scenes
- Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
- Morphological Neuron Classification Using Machine Learning
- Dendritic error backpropagation in deep cortical microcircuits
- Markerless tracking of user-defined features with deep learning
- Synthesizing realistic neural population activity patterns using Generative Adversarial Networks