There are 2 repositories under approximate-computing topic.
A Reconfigurable RISC-V Core for Approximate Computing
Library of approximate arithmetic circuits
Generator of arithmetic circuits (multipliers, adders) and approximate circuits
Curated content for DNN approximation, acceleration ... with a focus on hardware accelerator and deployment
Approximate layers - TensorFlow extension
A library of VHDL components for Neural Networks
VECBEE: A Versatile Efficiency-Accuracy Configurable Batch Error Estimation Method for Greedy Approximate Logic Synthesis
Condor allows for the specification of synopsis-based streaming jobs on top of general dataflow systems. Condor provides a collection of twelve synopses and an integration to Apache Flink.
Software and Hardware models of Approximate Carry-Lookahead Adder with Intelligent Carry Judgement and Correction
VACSEM: Verifying Average Errors in Approximate Circuits Using Simulation-Enhanced Model Counting
GPU-accelerated Neural Network layers using Approximate Multiplications for PyTorch
Implementation of our proposed defense strategy against adversarial attacks "Defensive Approximation (DA)"
This repository contains approximate 8-bit multiplier Verilog code.
https://arxiv.org/abs/1910.09876
Carry Cut-Back Adder (CCBA) - An approximate adder circuit with artificially-built false timing paths
Code for the paper "Combining Gradients and Probabilities for Heterogeneours Approximation of Neural Networks"
Approximate Printed Machine Learning Classifiers
GeAr low latency adder implementation and error analysis
DeBAM : Decoder Based Approximate multiplier for Low Power Applications
MATLAB and HDL models of ACA-CSU approximate adders
Approximate Logic Synthesis of Random Forest classifiers
Repository accompanying the paper "Fixed-Posit: A Floating-Point Representation for Error-Resilient Applications" published in IEEE Transactions on Circuits and Systems II
AxQEMU: a Floating-Point Approximation-aware Emulator
Approximation Trade Offs in an Image Based Control System