DNN Accuracy

Deep neural network (DNN) accuracy is a central concern in artificial intelligence, focusing on improving the correctness of DNN predictions while addressing limitations in computational resources and hardware imperfections. Current research emphasizes techniques like dataset distillation, neural architecture search, and quantization to optimize DNNs for efficiency and accuracy across various architectures (e.g., CNNs, RNNs, transformers) and hardware platforms (including analog and neuromorphic computing). These advancements are crucial for deploying DNNs in resource-constrained environments and improving their reliability in real-world applications, impacting fields ranging from computer vision and natural language processing to autonomous driving and medical diagnosis.

Papers

October 7, 2024

MetaDD: Boosting Dataset Distillation with Neural Network Architecture-Invariant Generalization
Yunlong Zhao, Xiaoheng Deng, Xiu Su, Hongyan Xu, Xiuxing Li, Yijing Liu, Shan You
Neural Network Dataset Distillation Tiny ImageNet DNN Accuracy Cross Architecture Generalization

September 3, 2024

Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables
Alessio Burrello, Francesco Carlucci, Giovanni Pollo, Xiaying Wang, Massimo Poncino, Enrico Macii, Luca Benini, Daniele Jahier Pagliari
Deep Neural Network Optimization Purpose PPG Signal Software Deployment State of the Art Deep Blood Pressure DNN Accuracy Low Power Wearable

August 29, 2024

Reconsidering the energy efficiency of spiking neural networks
Zhanglu Yan, Zhenyu Bai, Weng-Fai Wong
Neural Network Energy Efficiency Dataflow Architecture DNN Accuracy

August 11, 2024

Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends
Jeffry Victor, Chunguang Wang, Sumeet K. Gupta
Comparative Evaluation Memory Computing DNN Accuracy Synaptic Feedback Crossbar Array Resistive Memory Artifact Design Memory Technology

April 21, 2024

EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder
Hasanul Mahmud, Kevin Desai, Palden Lama, Sushil K. Prasad
New Framework Supervised Autoencoder DNN Accuracy

April 4, 2024

A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data
Iqra Bano, Rachmad Vidya Wicaksana Putra, Alberto Marchisio, Muhammad Shafique
Global Impact NCD Method SNN Model DNN Accuracy

March 28, 2024

DeepSample: DNN sampling-based testing for operational accuracy assessment
Antonio Guerriero, Roberto Pietrantuono, Stefano Russo
Deep Neural Network Level Test DNN Accuracy Accuracy Measurement Deep Neural Network Classifier

January 25, 2024

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
Yaniv Blumenfeld, Itay Hubara, Daniel Soudry
Deep Neural Network Deep Network DNN Accuracy Directed Accumulator

December 11, 2023

U-SWIM: Universal Selective Write-Verify for Computing-in-Memory Neural Accelerators
Zheyu Yan, Xiaobo Sharon Hu, Yiyu Shi
DNN Accuracy Non Volatile Memory Neural Accelerator

October 28, 2023

Efficient kernel surrogates for neural network-based regression
Saad Qadeer, Andrew Engel, Amanda Howard, Adam Tsou, Max Vargas, Panos Stinis, Tony Chiang
Deep Neural Network Neural Tangent Kernel Deep Regression DNN Accuracy Width Neural Network Kernel Based Surrogate

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 29, 2023

NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
Hao-Lun Sun, Lei Hsiung, Nandhini Chandramoorthy, Pin-Yu Chen, Tsung-Yi Ho
Prompt Recovery Neural Network Inference DNN Accuracy DRAM Access Energy Low Voltage

June 6, 2023

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
Drew Linsley, Ivan F. Rodriguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret Livingstone, Thomas Serre
Neural Network Computational Neuroscience Visual Cortex DNN Accuracy ImageNet Accuracy Low Quality Model

March 2, 2023

Iterative Assessment and Improvement of DNN Operational Accuracy
Antonio Guerriero, Roberto Pietrantuono, Stefano Russo
Deep Neural Network Large Relevance Improvement DNN Model DNN Accuracy

February 27, 2023

Supervised Virtual-to-Real Domain Adaptation for Object Detection Task using YOLO
Akbar Satya Nugraha, Yudistira Novanto, Bayu Rahayudi
Annotated Dataset Detection Task YOLO Shake Hand DNN Accuracy Virtual Dataset

February 16, 2023

Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators
Malte J. Rasch, Charles Mackin, Manuel Le Gallo, An Chen, Andrea Fasoli, Frederic Odermatt, Ning Li, S. R. Nandakumar, Pritish Narayanan, Hsinyu Tsai, Geoffrey W. Burr, Abu Sebastian, Vijay Narayanan
Memory Computing DNN Accuracy Inference Workload Analog in Memory Computing Hardware Aware Training Memory Accelerator

February 8, 2023

CRAFT: Criticality-Aware Fault-Tolerance Enhancement Techniques for Emerging Memories-Based Deep Neural Networks
Thai-Hoang Nguyen, Muhammad Imran, Jaehyuk Choi, Joon-Sung Yang
DNN Accuracy Traditional CrAFT Non Volatile Memory Criticality Analysis Fault Resilience

December 29, 2022

Restricting to the chip architecture maintains the quantum neural network accuracy
Lucas Friedrich, Jonas Maziero
Quantum Physic Quantum Neural Network Variational Quantum Algorithm Quantum Machine Learning Model Chip Design DNN Accuracy Human Performance

December 5, 2022

Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators
Abhishek Tyagi, Yiming Gan, Shaoshan Liu, Bo Yu, Paul Whatmough, Yuhao Zhu
DNN Accelerator New Formulation DNN Accuracy Resilience Measure Transient Fault

October 27, 2022

Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks
Zhanglu Yan, Jun Zhou, Weng-Fai Wong
Neural Network Voice Conversion Neural Network Model DNN Accuracy

DNN Accuracy

Papers

MetaDD: Boosting Dataset Distillation with Neural Network Architecture-Invariant Generalization

Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables

Reconsidering the energy efficiency of spiking neural networks

Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends

EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder

A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data

DeepSample: DNN sampling-based testing for operational accuracy assessment

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators

U-SWIM: Universal Selective Write-Verify for Computing-in-Memory Neural Accelerators

Efficient kernel surrogates for neural network-based regression

A Blueprint for Precise and Fault-Tolerant Analog Neural Networks

NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

Iterative Assessment and Improvement of DNN Operational Accuracy

Supervised Virtual-to-Real Domain Adaptation for Object Detection Task using YOLO

Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators

CRAFT: Criticality-Aware Fault-Tolerance Enhancement Techniques for Emerging Memories-Based Deep Neural Networks

Restricting to the chip architecture maintains the quantum neural network accuracy

Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators

Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks