Analog Neural Network

Analog neural networks (ANNs) aim to leverage the energy efficiency and speed of analog circuits for implementing artificial neural networks, addressing the power and scalability limitations of digital approaches. Current research focuses on mitigating the effects of hardware noise through novel regularization techniques and denoising blocks, developing hybrid digital-analog training methods like Equilibrium Propagation, and exploring diverse architectures such as Deep Hopfield Networks and KirchhoffNets. This field is significant for its potential to enable energy-efficient AI at the edge, particularly in applications like medical imaging and robotics, where low-power consumption and fast inference are crucial.

Papers

November 7, 2024

Impact of white noise in artificial neural networks trained for classification: performance and noise mitigation strategies
Nadezhda Semenova, Daniel Brunner
Neural Network Classification Code System Performance Softmax Function Neural Computation Analog Neural Network Background Noise Mitigating Noise

September 27, 2024

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators
Seyedarmin Azizi, Mohammad Erfan Sadeghi, Mehdi Kamal, Massoud Pedram
Deep Neural Network Native Robustness Denoising Process DNN Framework Inference Efficiency Analog Neural Network Mixed Signal Mitigating Noise

September 13, 2024

Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations
Alice Duque, Pedro Freire, Egor Manuylovich, Dmitrii Stoliarov, Jaroslaw Prilepsky, Sergei Turitsyn
Deep Learning Architecture Noise Robustness Analog Neural Network Noise Tolerant Network Noise Based Explanation Regularization

September 5, 2024

Towards training digitally-tied analog blocks via hybrid gradient computation
Timothy Nest, Maxence Ernoult
Analog Neural Network Analog Circuit Design Analog Accelerator

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 13, 2024

The Promise of Analog Deep Learning: Recent Advances, Challenges and Opportunities
Aditya Datar, Pramit Saha
Deep Neural Network Technical Challenge Emerging Opportunity Recent Advance Promise Analog Neural Network AI Hardware

May 13, 2024

Impact of white Gaussian internal noise on analog echo-state neural networks
Nadezhda Semenova
Neural Network Global Impact Gaussian Noise Echo State Network Analog Neural Network Reservoir Dynamic Correlated Noise Internal Noise

April 8, 2024

Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Jichang Yang, Hegan Chen, Jia Chen, Songqi Wang, Shaocong Wang, Yifei Yu, Xi Chen, Bo Wang, Xinyuan Zhang, Binbin Cui, Yi Li, Ning Lin, Meng Xu, Yi Li, Xiaoxin Xu, Xiaojuan Qi, Zhongrui Wang, Xumeng Zhang, Dashan Shang, Han Wang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Differential Equation Score Based Diffusion Model Analog Neural Network Resistive Memory Fast Generation

February 1, 2024

January 5, 2024

Digital-analog quantum learning on Rydberg atom arrays
Jonathan Z. Lu, Lucy Jiao, Kristina Wolinski, Milan Kornjača, Hong-Ye Hu, Sergio Cantu, Fangli Liu, Susanne F. Yelin, Sheng-Tao Wang
Analog Neural Network Quantum Gate Rydberg Atom Quantum Phase Recognition

November 1, 2023

Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial
Sam Dillavou, Benjamin D Beyer, Menachem Stern, Andrea J Liu, Marc Z Miskin, Douglas J Durian
Machine Learning Non Linear Analog Neural Network Linear Network Emergent Intelligence Metamaterial Neural Network Nonlinear Waveguide

October 24, 2023

September 29, 2023

Temporal credit assignment for one-shot learning utilizing a phase transition material
Alessandro R. Galloni, Yifan Yuan, Minning Zhu, Haoming Yu, Ravindra S. Bisht, Chung-Tse Michael Wu, Christine Grienberger, Shriram Ramanathan, Aaron D. Milstein
Analog Neural Network Biological Learning Brain Computation Temporal Credit Assignment One Shot Learning

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

June 15, 2023

Leveraging Residue Number System for Designing High-Precision Analog Deep Neural Network Accelerators
Cansu Demirkiran, Rashmi Agrawal, Vijay Janapa Reddi, Darius Bunandar, Ajay Joshi
Low Precision Analog Neural Network Analog Accelerator Residue Number

June 5, 2023

Best of Both Worlds: Hybrid SNN-ANN Architecture for Event-based Optical Flow Estimation
Shubham Negi, Deepika Sharma, Adarsh Kumar Kosta, Kaushik Roy
World Event Event Based Camera Analog Neural Network Hybrid Neural Network Event Based Optical Flow Stereo Event Camera

May 17, 2023

AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing
Hadjer Benmeziane, Corey Lammie, Irem Boybat, Malte Rasch, Manuel Le Gallo, Hsinyu Tsai, Ramachandran Muralidhar, Smail Niar, Ouarnoughi Hamza, Vijay Narayanan, Abu Sebastian, Kaoutar El Maghraoui
Deep Neural Network Exact Inference Analog Neural Network Inference Accelerator Analog in Memory Computing

May 15, 2023

Neural Oscillators are Universal
Samuel Lanthaler, T. Konstantin Rusch, Siddhartha Mishra
Analog Neural Network Physical Neural Network Neural Oscillation Harmonic Oscillator

Analog Neural Network

Papers

Impact of white noise in artificial neural networks trained for classification: performance and noise mitigation strategies

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators

Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations

Towards training digitally-tied analog blocks via hybrid gradient computation

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

The Promise of Analog Deep Learning: Recent Advances, Challenges and Opportunities

Impact of white Gaussian internal noise on analog echo-state neural networks

Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model

Analog In-Memory Computing with Uncertainty Quantification for Efficient Edge-based Medical Imaging Segmentation

Analog-digital Scheduling for Federated Learning: A Communication-Efficient Approach

Digital-analog quantum learning on Rydberg atom arrays

Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial

KirchhoffNet: A Scalable Ultra Fast Analog Neural Network

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

Temporal credit assignment for one-shot learning utilizing a phase transition material

A Blueprint for Precise and Fault-Tolerant Analog Neural Networks

Leveraging Residue Number System for Designing High-Precision Analog Deep Neural Network Accelerators

Best of Both Worlds: Hybrid SNN-ANN Architecture for Event-based Optical Flow Estimation

AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing

Neural Oscillators are Universal