Alice
Project
Home
Simulation Replay
Worldview
Version Log
Mind Research
中文
🧠 Neuroscience
Foundations
Neuroanatomy
Cellular & Molecular Neuroscience
Systems Neuroscience
Cognitive Neuroscience
Computational Neuroscience
Brain-Computer Interface
Neurotech Frontiers
Neuro Disorders
Computational Neuroscience
Spiking Neural Network (SNN) — Neuromorphic Computing
Predictive Coding
Bayesian Brain
Hopfield Networks
Grid Cells — Neural Spatial Map
Reinforcement Learning in the Brain
Free Energy Principle
Attractor Networks
Neural Population Dynamics
Drift-Diffusion Model
Efficient Coding Hypothesis
Divisive Normalization
Synaptic Plasticity Models
Deep Learning vs Brain
Reservoir Computing
Compartmental Models
Whole-Brain Modeling
Information Theory in Neuroscience
Neural ODEs & Continuous-Time Models
Energy-Based Models & the Brain
Table of Contents
1. Motivation
2. Neural ODE (Chen 2018)
3. Isomorphic to Neuroscience Models
4. PyTorch — Neural ODE (rate model)
5. Latent ODE — Irregular Sampling
6. Stiff ODE Problem
7. Relation to RNN / Continuous RNN
8. Pros and Cons
9. Neuroscience Applications
10. Common Pitfalls
10.1 Neural ODE Brand New
10.2 Any ODE Solver
10.3 Adjoint Always Saves Memory
10.4 Continuous = More Biological
10.5 Always Better Than RNN
11. Related Concepts
References