m4urin/quantized-liquid-state-machines

A Liquid State Machine using quantized neurons that are operating on lower-bit representations and fixed point computations. It provides a next step towards the implementation of efficient accelerators that can be used in the field of neuromorphic computing.

27
/ 100
Experimental

This project helps neuromorphic computing researchers and hardware engineers design and evaluate more efficient brain-inspired AI systems. It takes in parameters like neuron bit representation, liquid size, and time series encoding, then outputs measures of prediction accuracy and computational efficiency for a given Liquid State Machine configuration. The primary users are those focused on optimizing the power and speed of neuromorphic hardware.

No commits in the last 6 months.

Use this if you are a neuromorphic computing researcher or hardware designer exploring the trade-offs between accuracy and efficiency in quantized Liquid State Machines.

Not ideal if you are looking for a general-purpose machine learning library or a tool for applying pre-built models to real-world data.

neuromorphic-computing hardware-acceleration spiking-neural-networks low-power-AI brain-inspired-computing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Apr 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/m4urin/quantized-liquid-state-machines"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.