DNN Framework

Deep neural network (DNN) frameworks are the foundation of modern artificial intelligence, aiming to improve model accuracy, efficiency, and robustness. Current research focuses on optimizing DNN training and inference, including techniques like efficient parallelization strategies, mixed-precision training, and adaptive model selection based on resource constraints and carbon footprint. These advancements are crucial for deploying DNNs on resource-limited devices (e.g., edge computing) and mitigating challenges like adversarial attacks, noise, and data scarcity, ultimately impacting various fields from computer vision to natural language processing.

Papers

September 20, 2023

Prototype of a robotic system to assist the learning process of English language with text-generation through DNN
Carlos Morales-Torres, Mario Campos-Soberanis, Diego Campos-Sobrino
Natural Language Processing Long Short Term Memory Text Generation Robotic System Humanoid Robot DNN Framework Learning Process

September 12, 2023

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
Yanzuo Chen (1), Zhibo Liu (1), Yuanyuan Yuan (1), Sihang Hu (2), Tianxiang Li (2), Shuai Wang (1) ((1) The Hong Kong University of Science and Technology, (2) Huawei Technologies)
DNN Framework Bit Flip Attack Bit Flip

September 4, 2023

On the fly Deep Neural Network Optimization Control for Low-Power Computer Vision
Ishmeet Kaur, Adwaita Janardhan Jadhav
Neural Network Pre Trained Edge Device DNN Framework Low Power Computer Vision Edge Speech Application

August 29, 2023

From DDMs to DNNs: Using process data and models of decision-making to improve human-AI interactions
Mrugsen Nagsen Gopnarayan, Jaan Aru, Sebastian Gluth
Artificial Intelligence Multi Agent Decision Making DNN Framework Behavioral Economics Human Artificial Intelligence Process Data

August 14, 2023

Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling
Lequn Chen, Weixin Deng, Anirudh Canumalla, Yu Xin, Danyang Zhuo, Matthai Philipose, Arvind Krishnamurthy
DNN Framework DNN Model Dynamic Scheduling DNN Inference Phantom 2D Accelerator

August 3, 2023

Assessing Systematic Weaknesses of DNNs using Counterfactuals
Sujan Sai Gannamaneni, Michael Mock, Maram Akila
Semantic Segmentation Model DNN Framework High Quality Counterfactuals Semantic Feature Physical Weakness

July 29, 2023

An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks
Ye Tao, Wanwei Liu, Fu Song, Zhen Liang, Ji Wang, Hongxu Zhu
Neural Network Deep Neural Network DNN Framework Multiplier Free Quantization Quantized Neural Network Automaton Theoretic Approach

July 20, 2023

Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing
Dong Huang, Qingwen Bu, Yichao Fu, Yuhao Qing, Bocheng Xiao, Heming Cui
Deep Neural Network DNN Framework Unlabeled Data DNN Model Deep Learning Testing

July 19, 2023

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
Young D. Kwon, Rui Li, Stylianos I. Venieris, Jagmohan Chauhan, Nicholas D. Lane, Cecilia Mascolo
DNN Framework Device Training Energy Efficient Training Sparse Update Edge Data

July 13, 2023

Deep Neural Networks for Semiparametric Frailty Models via H-likelihood
Hangbin Lee, IL DO HA, Youngjo Lee
Deep Neural Network DNN Framework Negative Log Likelihood Frailty Care Competing Risk

July 11, 2023

June 16, 2023

Representation and decomposition of functions in DAG-DNNs and structural network pruning
Wen-Liang Hwang
Deep Neural Network Individual Representation DNN Framework Microbial Decomposition Simple Function Network Pruning

May 23, 2023

Transferring Learning Trajectories of Neural Networks
Daiki Chijiwa
Neural Network Deep Neural Network Pre Trained Model DNN Framework

May 16, 2023

A Note on Dimensionality Reduction in Deep Neural Networks using Empirical Interpolation Method
Harbir Antil, Madhu Gupta, Randy Price
Deep Neural Network Dimensionality Reduction DNN Framework Short Note Parametric Approximation Empirical Interpolation Method

May 9, 2023

A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks
Mohammad Hasan Ahmadilivani, Mahdi Taheri, Jaan Raik, Masoud Daneshtalab, Maksim Jenihhin
Deep Neural Network DNN Framework Systematic Literature Review

April 26, 2023

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs
Mingjie Li, Quanshi Zhang
Deep Neural Network Line by Line Explanation Technical Report DNN Framework Logical Inference Low Complexity Explanation

April 19, 2023

Adaptive Scheduling for Edge-Assisted DNN Serving
Jian He, Chenxi Yang, Zhaoyuan He, Ghufran Baig, Lili Qiu
Deep Neural Network DNN Framework Adaptive Scheduling

April 8, 2023

FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement
Xiaonan Nie, Xupeng Miao, Zilong Wang, Zichao Yang, Jilong Xue, Lingxiao Ma, Gang Cao, Bin Cui
Mixture of Expert Model Training DNN Framework Sparse Model Large Scale Pre Trained Model Device Placement Conditional Computation

March 29, 2023

Latent Feature Relation Consistency for Adversarial Robustness
Xingbin Liu, Huafeng Kuang, Hong Liu, Xianming Lin, Yongjian Wu, Rongrong Ji
Deep Neural Network Adversarial Example Adversarial Robustness DNN Framework Latent Feature Imperceptible Adversarial Perturbation Latent Consistency Model

DNN Framework

Papers

Prototype of a robotic system to assist the learning process of English language with text-generation through DNN

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables

On the fly Deep Neural Network Optimization Control for Low-Power Computer Vision

From DDMs to DNNs: Using process data and models of decision-making to improve human-AI interactions

Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling

Assessing Systematic Weaknesses of DNNs using Counterfactuals

An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks

Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge

Deep Neural Networks for Semiparametric Frailty Models via H-likelihood

Membership Inference Attacks on DNNs using Adversarial Perturbations

DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization

Representation and decomposition of functions in DAG-DNNs and structural network pruning

Transferring Learning Trajectories of Neural Networks

A Note on Dimensionality Reduction in Deep Neural Networks using Empirical Interpolation Method

A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs

Adaptive Scheduling for Edge-Assisted DNN Serving

FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement

Latent Feature Relation Consistency for Adversarial Robustness