Skip to content

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

LiquidLab — Interactive Liquid Neural Networks & Continuous-Time Models Laboratory

MIT License Deploy

An interactive browser-based laboratory for exploring Liquid Neural Networks (LNNs) — the brain-inspired continuous-time adaptive architecture developed at MIT CSAIL by Ramin Hasani, Mathias Lechner, and Daniela Rus.

Inspired by the 302-neuron C. elegans nematode brain, liquid neural networks use differential equations with learnable time constants that adapt their dynamics based on input — enabling real-time adaptation, extreme parameter efficiency, and continuous-depth computation.

6 Interactive Modules

1. LTC Neuron Dynamics

Explore a single Liquid Time-Constant neuron. Adjust parameters to see how the adaptive time constant τ(x, I) enables variable-timescale processing.

2. Neural ODE Playground

Compare continuous-depth (Neural ODE) vs discrete-layer computation. Visualize Euler vs RK4 trajectories through learned vector fields (spiral, saddle, limit cycle).

3. C. elegans Connectome Explorer

Interactive force-directed visualization of the 302-neuron nematode brain — the biological blueprint for liquid networks. Color-coded by neuron type.

4. Closed-Form Continuous (CfC) Networks

The breakthrough that made liquid nets practical: analytical closed-form solutions eliminate expensive ODE solvers, achieving N× speedup with zero accuracy loss.

5. Adaptive Inference Demo

Watch a tiny liquid network adapt in real-time to concept drift (sine→square, slow→fast, clean→noisy) while a frozen LSTM fails. No retraining needed.

6. Efficiency Arena

Compare Liquid vs LSTM vs Transformer vs Mamba on parameters, FLOPs, and memory. See why 19 neurons can drive a car.

Tech Stack

  • Single HTML file, vanilla JavaScript, HTML5 Canvas
  • Zero dependencies, zero build step
  • Deployed on Vercel

Key References

  • Hasani et al. "Liquid Time-constant Networks" (AAAI 2021)
  • Hasani et al. "Closed-form Continuous-time Neural Networks" (Nature Machine Intelligence 2022)
  • White et al. "The Structure of the Nervous System of C. elegans" (1986)
  • Liquid AI — https://liquid.ai

License

MIT

About

LiquidLab — Interactive Liquid Neural Networks & Continuous-Time Models Laboratory. 6 modules: LTC dynamics, Neural ODE, C. elegans connectome, CfC networks, adaptive inference, efficiency arena. Zero dependencies.

Topics

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages