Intelligent Microsystems Lab's repositories
QuantizedLSTM
Models and training scripts for "LSTMs for Keyword Spotting with ReRAM-based Compute-In-Memory Architectures" (ISCAS 2021).
QuantizedSNNs
This repository contains the models and training scripts used in the papers: "Quantizing Spiking Neural Networks with Integers" (ICONS 2020) and "Memory Organization for Energy-Efficient Learning and Inference in Digital Neuromorphic Accelerators" (ISCAS 2020).
SNNQuantPrune
Code for the ISCAS23 paper "The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networks"
Network_Analysis
Pytorch code to view the effectiveness of a neural network over time using the Henze-Penrose statistic and Fisher permutation test for means.
jax_squant
PTQ using SQuant paper in JAX
slayerPytorch
Modified version of SLAYER including pruning and dropout techniques
timeloop-quant
This version supports per-operand precision