Artificial Neural Networks for Neuroscientists: A Primer
By Guangyu Robert Yang, Xiao-Jing Wang. Neuron, 2020
325 citations recorded by the source corpus.
SUMMARY 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 readers garner hands-on experience, this Primer is accompanied with tutorial-style code in PyTorch and Jupyter Notebook, covering major topics.
Subfields: Biophysics, Cognitive Neuroscience
View Paper: https://www.semanticscholar.org/paper/0ea77c0b9ce9959435a2b24dfd37d1bf1097d66b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
Citations in the corpus
- Interpreting neural computations by examining intrinsic and embedding dimensionality of neural activity (2021, background): “A promising approach for addressing this question is to exploit model reduction techniques to reverse-engineer large recurrent networks trained on the task using techniques inspired by artificial intelligence [88].”
- Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation (2024, background): “Inspired by the hierarchical advantages of the mammalian visual processing system [15, 19, 29, 33, 55, 70], we pro-pose to inject multi-level supervision in our continual model and aggregate the skills from different experts within it (see Fig.”