Artificial Neural Networks for Neuroscientists: A Primer

2020/06/01 by Guangyu Robert Yang, Xiao-Jing Wang, Xiao‐Jing Wang · 2 voices · 4 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Neuroscience · #Cell Image Analysis Techniques #Functional Brain Connectivity Studies #Neural dynamics and brain function #cs.LG #q-bio.NC

paper · pdf · doi:10.1016/j.neuron.2020.09.005

arxiv published 2020/06/01 · openalex created_date 2020/06/05 · openalex publication_date 2020/09/01 · arxiv updated 2020/09/24 · openalex updated_date 2026/07/28

Abstract

Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience. Besides offering powerful techniques for data analysis, ANNs provide a new approach for neuroscientists to build models for complex behaviors, heterogeneous neural activity and circuit connectivity, as well as to explore optimization in neural systems, in ways that traditional models are not designed for. In this pedagogical Primer, we introduce ANNs and demonstrate how they have been fruitfully deployed to study neuroscientific questions. We first discuss basic concepts and methods of ANNs. Then, with a focus on bringing this mathematical framework closer to neurobiology, we detail how to customize the analysis, structure, and learning of ANNs to better address a wide range of challenges in brain research. To help the readers garner hands-on experience, this Primer is accompanied with tutorial-style code in PyTorch and Jupyter Notebook, covering major topics.

Citations

• Intriguing properties of neural networks
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• On the difficulty of training Recurrent Neural Networks
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Auto-Encoding Variational Bayes
• A Stochastic Approximation Method
• The perceptron: A probabilistic model for information storage and organization in the brain.
• Finding Structure in Time
• Gradient-based learning applied to document recognition
• Visual attention: The past 25 years
• Short-Term Synaptic Plasticity
• On the control of automatic processes: A parallel distributed processing account of the Stroop effect.
• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• Neural Machine Translation by Jointly Learning to Align and Translate
• Learning to Forget: Continual Prediction with LSTM
• Multilayer feedforward networks are universal approximators
• ImageNet classification with deep convolutional neural networks
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Opening the Black Box of Deep Neural Networks via Information
• SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks
• Neural population control via deep image synthesis
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• TensorFlow: A system for large-scale machine learning
• Universality and individuality in neural dynamics across large populations of recurrent networks
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Backpropagation and the brain
• Layer Normalization
• Generative Adversarial Nets
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems

Cited by

• Biomarkers of brain diseases
• Efficient planning and implementation of optimal foraging strategies under energetic constraints
• Dynamical Mechanism of Sampling-based Stochastic Inference under Probabilistic Population Codes
• Biologically plausible models of cognitive flexibility: merging recurrent neural networks with full-brain dynamics

Discussions

• Artificial neural networks for neuroscientists: A primer [hn, 3 points, 1 comments]
• Artificial neural networks for neuroscientists: A primer [hn, 1 points, 0 comments]

Related

• Testing the Tools of Systems Neuroscience on Artificial Neural Networks
• Neural Networks, Artificial Intelligence and the Computational Brain
• Biological Blueprints for Next Generation AI Systems
• Fundamentals in Neurocomputing
• Brain-inspired learning in artificial neural networks: a review