https://github.com/aygp-dr/liquid-neural-networks
Liquid Neural Networks (LNN) - Continuous-time neural dynamics inspired by C. elegans. Parameter-efficient AI with 19-302 neurons for complex tasks. Hybrid Clojure/Python implementation.
https://github.com/aygp-dr/liquid-neural-networks
clojure neural-networks python research
Last synced: 10 months ago
JSON representation
Liquid Neural Networks (LNN) - Continuous-time neural dynamics inspired by C. elegans. Parameter-efficient AI with 19-302 neurons for complex tasks. Hybrid Clojure/Python implementation.
- Host: GitHub
- URL: https://github.com/aygp-dr/liquid-neural-networks
- Owner: aygp-dr
- License: mit
- Created: 2025-07-17T10:06:19.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-07-28T11:40:24.000Z (12 months ago)
- Last Synced: 2025-09-14T20:01:45.069Z (10 months ago)
- Topics: clojure, neural-networks, python, research
- Language: Python
- Homepage: https://github.com/jwalsh/liquid-neural-networks
- Size: 130 KB
- Stars: 5
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.org
- License: LICENSE
Awesome Lists containing this project
README
#+TITLE: Liquid Neural Networks
#+AUTHOR: Aidan Pace
#+DATE: 2025-01-17
#+OPTIONS: toc:2 num:nil ^:nil
[[https://github.com/aygp-dr/liquid-neural-networks/blob/main/LICENSE][https://img.shields.io/badge/license-MIT-blue.svg]]
[[https://github.com/aygp-dr/liquid-neural-networks][https://img.shields.io/badge/python-3.9+-blue.svg]]
[[https://github.com/aygp-dr/liquid-neural-networks][https://img.shields.io/badge/clojure-1.11+-blue.svg]]
[[https://github.com/aygp-dr/liquid-neural-networks][https://img.shields.io/badge/status-draft-orange.svg]]
[[https://github.com/aygp-dr/liquid-neural-networks/releases][https://img.shields.io/badge/release-v0.1.0-blue.svg]]
* Overview
*🚧 Project Status: Draft/In Progress*
This project is in early development. Core algorithms and implementations are being actively developed.
Liquid Neural Networks (LNNs) are a revolutionary approach to artificial intelligence that draws inspiration from biological neural systems, particularly the C. elegans nervous system. Unlike traditional neural networks, LNNs use continuous-time dynamics and can adapt in real-time to changing inputs.
** Key Features
- *Parameter Efficiency*: Solve complex tasks with as few as 19-302 neurons
- *Continuous-Time Dynamics*: Based on ordinary differential equations (ODEs)
- *Real-Time Adaptation*: Networks that evolve and adapt during inference
- *Superior Interpretability*: Understand exactly how decisions are made
- *Edge AI Ready*: Efficient enough for deployment on resource-constrained devices
** Why Liquid Neural Networks?
Traditional neural networks require millions of parameters and struggle with:
- Adapting to new situations without retraining
- Explaining their decision-making process
- Running efficiently on edge devices
- Handling time-series data naturally
LNNs address these limitations by mimicking biological neurons more closely, using differential equations to model continuous-time dynamics.
* Quick Start
** Installation
*** Python
#+begin_src bash
# Using pip
pip install liquid-neural-networks
# Using uv (recommended)
uv pip install liquid-neural-networks
# Development installation
git clone https://github.com/aygp-dr/liquid-neural-networks
cd liquid-neural-networks
uv pip install -e ".[dev]"
#+end_src
*** Clojure
#+begin_src bash
# Add to your deps.edn
{:deps {aygp-dr/liquid-neural-networks {:git/url "https://github.com/aygp-dr/liquid-neural-networks"
:git/sha "LATEST_SHA"}}}
# Or use from source
git clone https://github.com/aygp-dr/liquid-neural-networks
cd liquid-neural-networks
clojure -M:dev
#+end_src
** Basic Usage
*** Python Example
#+begin_src python
from liquid_neural_networks import LiquidNeuron, LiquidNetwork
# Create a simple liquid neural network
network = LiquidNetwork(
input_size=10,
hidden_size=32, # Just 32 neurons!
output_size=2
)
# Train on time-series data
for epoch in range(100):
outputs = network(inputs, time_constants)
loss = criterion(outputs, targets)
loss.backward()
#+end_src
*** Clojure Example
#+begin_src clojure
(require '[liquid-neural-networks.core :as lnn])
;; Create a liquid network
(def network (lnn/create-network {:input-size 10
:hidden-size 32
:output-size 2}))
;; Process time-series data
(def result (lnn/forward network input-data time-constants))
#+end_src
* Applications
** Autonomous Systems
- Drone navigation with 19 neurons
- Self-driving car control
- Robotic arm manipulation
** Time-Series Analysis
- Financial market prediction
- Weather forecasting
- Sensor data processing
** Medical Diagnostics
- ECG analysis
- Brain signal interpretation
- Disease progression modeling
** Edge AI
- IoT device intelligence
- Embedded system control
- Real-time anomaly detection
* Architecture
LNNs consist of three main components:
1. *Liquid Time-Constant (LTC) Neurons*: Neurons with adaptive time constants that change based on input
2. *Continuous-Time Dynamics*: ODEs that govern neuron behavior
3. *Sparse Connectivity*: Efficient wiring patterns inspired by biological systems
The mathematical foundation:
#+begin_example
dx/dt = -x/Ï„(t) + f(Wx + b)
where Ï„(t) is the adaptive time constant
#+end_example
* Performance
Benchmark results comparing LNNs to traditional architectures:
| Task | Traditional NN | LNN | Parameters Reduction |
|------+---------------+-----+---------------------|
| Drone Control | 100K params | 19 neurons | 99.98% |
| Time-Series | 1M params | 302 neurons | 99.97% |
| Image Classification | 25M params | 1K neurons | 99.99% |
* Contributing
We welcome contributions! See our [[file:CONTRIBUTING.org][Contributing Guide]] for:
- Code style guidelines
- Testing requirements
- Pull request process
- Development setup
* Documentation
- [[file:docs/tutorials/][Tutorials]]: Step-by-step guides
- [[file:docs/api/][API Reference]]: Detailed documentation
- [[file:examples/][Examples]]: Working code samples
- [[file:SETUP.org][Development Setup]]: For contributors
* Research
This implementation is based on:
- Hasani et al. "Liquid Time-constant Networks" (2021)
- Lechner et al. "Neural Circuit Policies" (2020)
- MIT CSAIL research on continuous-time neural models
* License
MIT License - see [[file:LICENSE][LICENSE]] for details.
* Community
- [[https://github.com/aygp-dr/liquid-neural-networks/discussions][GitHub Discussions]]
- [[https://github.com/aygp-dr/liquid-neural-networks/issues][Issue Tracker]]
- Research papers and citations in [[file:docs/papers/][docs/papers/]]