Analog Computing

Analog computing leverages the continuous nature of physical systems to perform computations, aiming for significantly improved energy efficiency and speed compared to digital approaches. Current research focuses on developing robust training algorithms for analog neural networks, exploring architectures like memristive neural ODE solvers and Hopfield networks, and addressing challenges such as non-associativity and noise inherent in analog hardware. This renewed interest in analog computing is driven by the need for more energy-efficient AI and the potential for breakthroughs in areas like digital twinning, real-time signal processing (e.g., ECG analysis), and edge computing applications.

Papers

January 6, 2025

Analogue Forecast System for Daily Precipitation Prediction Using Autoencoder Feature Extraction: Application in Hong Kong
Yee Chun Tsoi, Yu Ting Kwok, Ming Chun Lam, Wai Kin Wong
Application Proficiency Rural China Neural Network Autoencoder Precipitation Prediction Analog Computing Ecmwf Reanalysis V5

December 30, 2024

Analog Alchemy: Neural Computation with In-Memory Inference, Learning and Routing
Yigit Demirag
LeArning Abstract Routing Problem Memristive Device Neural Computation Analog Computing Analog Domain Inference Memory Usage

December 3, 2024

Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing
Nanyang Ye, Qiao Sun, Yifei Wang, Liujia Yang, Jundong Zhou, Lei Wang, Guang-Zhong Yang, Xinbing Wang, Chenghu Zhou, Huaqiang Wu, Qinying Gu
Practical Algorithm Memristive Device Synergistic Information Analog Computing

November 19, 2024

Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training
Tengji Xu, Zeyu Luo, Shaojie Liu, Li Fan, Qiarong Xiao, Benshan Wang, Dongliang Wang, Chaoran Huang
Native Robustness Analog Computing Physical Neural Network Device Model Sharpness Aware Training

October 30, 2024

KALAM: toolKit for Automating high-Level synthesis of Analog computing systeMs
Ankita Nandi, Krishil Gandhi, Mahendra Pratap Singh, Shantanu Chakrabartty, Chetan Singh Thakur
System Description Decomposed Automation Correction Margin Classifier High Level Synthesis Analog Computing

June 18, 2024

Towards Exact Gradient-based Training on Analog In-memory Computing
Zhaoxian Wu, Tayfun Gokmen, Malte J. Rasch, Tianyi Chen
Training Data Gradient Based Analog Neural Network Analog in Memory Computing Analog Computing Energy Efficient AI Analog Accelerator

June 12, 2024

Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver
Hegan Chen, Jichang Yang, Jia Chen, Songqi Wang, Shaocong Wang, Dingchen Wang, Xinyu Tian, Yifei Yu, Xi Chen, Yinan Lin, Yangu He, Xiaoshan Wu, Yi Li, Xinyuan Zhang, Ning Lin, Meng Xu, Yi Li, Xumeng Zhang, Zhongrui Wang, Han Wang, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Digital Twin Differential Equation Memristive Device Analog Computing

May 22, 2024

Thermodynamic Natural Gradient Descent
Kaelan Donatella, Samuel Duffield, Maxwell Aifer, Denis Melanson, Gavin Crooks, Patrick J. Coles
Gradient Descent Natural Gradient Second Order Natural Gradient Descent Analog Computing Virtual Analog

December 22, 2023

Energy-based learning algorithms for analog computing: a comparative study
Benjamin Scellier, Maxence Ernoult, Jack Kendall, Suhas Kumar
Contrastive Learning Comparative Study Learning Algorithm Energy Based Analog Computing

November 17, 2023

On exploiting the synaptic interaction properties to obtain frequency-specific neurons
Guillaume Marthe, Claire Goursaud, Romain Cazé, Laurent Clavier
Circuit Design Spike Timing Synaptic Connectivity Analog Computing Synaptic Delay Task Specific Neuron

November 13, 2023

Pruning random resistive memory for optimizing analogue AI
Yi Li, Songqi Wang, Yaping Zhao, Shaocong Wang, Woyu Zhang, Yangu He, Ning Lin, Binbin Cui, Xi Chen, Shiming Zhang, Hao Jiang, Peng Lin, Xumeng Zhang, Xiaojuan Qi, Zhongrui Wang, Xiaoxin Xu, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Edge Pruning Analog Computing Resistive Memory

October 24, 2023

EKGNet: A 10.96{\mu}W Fully Analog Neural Network for Intra-Patient Arrhythmia Classification
Benyamin Haghi, Lin Ma, Sahin Lale, Anima Anandkumar, Azita Emami
Deep Learning Analog Neural Network Analog Computing Virtual Analog Arrhythmia Classification

September 30, 2023

Quantization of Deep Neural Networks to facilitate self-correction of weights on Phase Change Memory-based analog hardware
Arseni Ivanov
Deep Neural Network Quantization Operator Phase Transition Neural Network Weight Self Correction Analog Computing Self Improving Analog Layout

September 25, 2023

On the Non-Associativity of Analog Computations
Lisa Kuhn, Bernhard Klein, Holger Fröning
Neural Network Variant Pathogenicity Analog Computing Analog Domain Non Associativity

September 23, 2023

Machine Learning with Chaotic Strange Attractors
Bahadır Utku Kesgin, Uğur Teğin
Neural Network Machine Learning Neuromorphic Computing Analog Computing Chaotic Attractor

September 19, 2023

A Blueprint for Precise and Fault-Tolerant Analog Neural Networks
Cansu Demirkiran, Lakshmi Nair, Darius Bunandar, Ajay Joshi
Analog Neural Network DNN Accuracy Analog Computing Blueprint Architecture Analog Accelerator

July 18, 2023

Extreme heatwave sampling and prediction with analog Markov chain and comparisons with deep learning
George Miloshevich, Dario Lucente, Pascal Yiou, Freddy Bouchet
Deep Learning Human Prediction Climate Model Comparative Review Climate Simulation Analog Computing Pseudo Sample

October 10, 2022

Training Spiking Neural Networks with Local Tandem Learning
Qu Yang, Jibin Wu, Malu Zhang, Yansong Chua, Xinchao Wang, Haizhou Li
Local Feature Analog Computing

August 24, 2022

How (and Why) to Think that the Brain is Literally a Computer
Corey J. Maley
Computation Method Brain Function Computational Approach Digital Computer Analog Computing Computational System

May 11, 2022

Process, Bias and Temperature Scalable CMOS Analog Computing Circuits for Machine Learning
Pratik Kumar, Ankita Nandi, Shantanu Chakrabartty, Chetan Singh Thakur
Machine Learning Absolute Stance Bias Complex Process Complementary Metal Oxide Semiconductor Analog Computing Digital Circuit

Analog Computing

Papers

Analogue Forecast System for Daily Precipitation Prediction Using Autoencoder Feature Extraction: Application in Hong Kong

Analog Alchemy: Neural Computation with In-Memory Inference, Learning and Routing

Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing

Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training

KALAM: toolKit for Automating high-Level synthesis of Analog computing systeMs

Towards Exact Gradient-based Training on Analog In-memory Computing

Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver

Thermodynamic Natural Gradient Descent

Energy-based learning algorithms for analog computing: a comparative study

On exploiting the synaptic interaction properties to obtain frequency-specific neurons

Pruning random resistive memory for optimizing analogue AI

EKGNet: A 10.96{\mu}W Fully Analog Neural Network for Intra-Patient Arrhythmia Classification

Quantization of Deep Neural Networks to facilitate self-correction of weights on Phase Change Memory-based analog hardware

On the Non-Associativity of Analog Computations

Machine Learning with Chaotic Strange Attractors

A Blueprint for Precise and Fault-Tolerant Analog Neural Networks

Extreme heatwave sampling and prediction with analog Markov chain and comparisons with deep learning

Training Spiking Neural Networks with Local Tandem Learning

How (and Why) to Think that the Brain is Literally a Computer

Process, Bias and Temperature Scalable CMOS Analog Computing Circuits for Machine Learning