Energy-efficient Event-driven Spiking Neural Network accelerator for FPGA with PyTorch integration

This repository is an implementation of LIF neuron model (Leaky Integrate and Fire), Adaptive LIF and Adaptive Exponential LIF from scratch.

Comparative study of event-driven vs clock-driven LIF spiking neuron implementations. Includes software simulation, FPGA hardware deployment, and analysis of decay strategies across multiple datasets (MNIST, N-MNIST, AudioMNIST)

This program generates two LIF neurons which are coupled by a chemical synapse.

graphs of a biological neuron's activity (LIF) and a perceptron's activity in Python

Leaky Integrate and fire model Example

Computational neuroscience simulation of stochastic resonance in LIF neurons using Python.

A Leaky Integrate-and-Fire (LIF) Neuron

Neural Preference Learning (NPL) is a novel architecture that gives LLM agents persistent, personal preferences by pairing them with a companion spiking neural network. Unlike RLHF (which is batch, pre-deployment, and population-level), NPL operates in real-time, learning from individual user feedback through natural language.

Python Leaky Integrate and Fire Tester -- A LIF implementation for learning purposes

RU--CS425