lif-neuron

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

Biological Leaky Integrate-and-Fire (LIF) neuromorphic simulator with membrane potential dynamics, refractory period, and discrete event spike emission.

Biological Leaky Integrate-and-Fire (LIF) neuromorphic simulator with membrane potential dynamics, refractory period, and discrete event spike emission.

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)

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

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

Simulation of a Leaky Integrate-and-Fire (LIF) neuron using Python, NumPy, and Matplotlib for neuromorphic computing research and education.

This repository is being used to store the work for my direct RTL neuron implementation that I am creating as part of my research project.

Web-based neural simulation platform for modeling, simulating, and analyzing neural systems using numerical solvers

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

Bio-inspired neuromorphic operating system (Rust + Python) that runs the complete Drosophila connectome (125M synapses) as an event-driven spiking network. Targets x86, ARM, Intel Loihi 2, FPGA. Apache-2.0.

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.

A lightweight, object-oriented C++ simulation of Leaky Integrate-and-Fire (LIF) spiking neurons and STDP synaptic learning, before I learn differential equations.

Hardware-based 3-layer SNN prototype (3-2-1 architecture) using discrete 74LS series logic. Features event-driven temporal pattern recognition via 74LS161 integration and 74LS85 thresholding. Validated at 10kHz with asynchronous RC reset loops to mimic biological refractory periods. Developed as a standalone hardware neural inference engine.

A Leaky Integrate-and-Fire (LIF) Neuron

RU--CS425

Interactive 3D computational neuroscience simulator for exploring brain regions, neural activity and neurochemical modulation. 🧠⚡