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

March 22, 2023

Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
Yanbiao Ma, Licheng Jiao, Fang Liu, Maoji Wen, Lingling Li, Wenping Ma, Shuyuan Yang, Xu Liu, Puhua Chen
Human Prediction Procedural Fairness DNN Framework Model Bias Model Fairness Gaussian Curvature

February 25, 2023

Does a Neural Network Really Encode Symbolic Concepts?
Mingjie Li, Quanshi Zhang
Neural Network DNN Framework Well Trained Discriminative Response Encoded Concept

February 23, 2023

Practical Knowledge Distillation: Using DNNs to Beat DNNs
Chung-Wei Lee, Pavlos Athanasios Apostolopulos, Igor L. Markov
Knowledge Distillation DNN Framework Gradient Boosting Model Distillation Deep Neural Network Performance Deep Neural Network Ensemble

February 20, 2023

A DNN based Normalized Time-frequency Weighted Criterion for Robust Wideband DoA Estimation
Kuan-Lin Chen, Ching-Hua Lee, Bhaskar D. Rao, Harinath Garudadri
DNN Framework Direction of Arrival Estimation Reverberant Environment Erase Based Masking Speaker Localization Mask Wearing Ratio

February 18, 2023

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics
Nihal Murali, Aahlad Puli, Ke Yu, Rajesh Ranganath, Kayhan Batmanghelich
Deep Neural Network Distribution Shift Camera Lens DNN Framework Model Generalization Training Dynamic Spurious Feature

February 4, 2023

NeuRI: Diversifying DNN Generation via Inductive Rule Inference
Jiawei Liu, Jinjun Peng, Yuyao Wang, Lingming Zhang
Deep Learning DNN Framework DNN Model Program Synthesis Fuzz Testing Inductive Inference

February 3, 2023

DynaMIX: Resource Optimization for DNN-Based Real-Time Applications on a Multi-Tasking System
Minkyoung Cho, Kang G. Shin
Autonomous Vehicle Multi Task Real Time DNN Framework Resource Optimization Vehicle Network

January 17, 2023

The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks
Luca Marzari, Davide Corsi, Ferdinando Cicalese, Alessandro Farinelli
Deep Neural Network DNN Framework State of the Art Verifier DNN Verification Unsafe Input Safety Benchmark DNN Verifier

January 14, 2023

Efficient Evaluation Methods for Neural Architecture Search: A Survey
Xiaotian Song, Xiangning Xie, Zeqiong Lv, Gary G. Yen, Weiping Ding, Jiancheng Lv, Yanan Sun
Deep Neural Network Timely Survey Neural Architecture Search DNN Framework Efficient Evaluation

January 7, 2023

ExcelFormer: Can a DNN be a Sure Bet for Tabular Prediction?
Jintai Chen, Jiahuan Yan, Qiyuan Chen, Danny Ziyi Chen, Jian Wu, Jimeng Sun
DNN Framework Tabular Deep Learning Tabular Prediction Tabular Prediction Task

December 26, 2022

Higher order organizational features can distinguish protein interaction networks of disease classes: a case study of neoplasms and neurological diseases
Vikram Singh, Vikram Singh
DNN Framework Disease Classification Higher Order Protein Protein Interaction Protein Interaction Network

December 16, 2022

Adversarial Example Defense via Perturbation Grading Strategy
Shaowei Zhu, Wanli Lyu, Bin Li, Zhaoxia Yin, Bin Luo
Deep Neural Network Adversarial Example Adversarial Perturbation DNN Framework

November 16, 2022

Efficiently Finding Adversarial Examples with DNN Preprocessing
Avriti Chauhan, Mohammad Afzal, Hrishikesh Karmarkar, Yizhak Elboher, Kumar Madhukar, Guy Katz
Neural Network Deep Neural Network Native Robustness Adversarial Example DNN Framework

November 11, 2022

Emergence of Concepts in DNNs?
Tim Räz
Path Breaking Emergence DNN Framework Internal Representation Concept Identification Hidden Layer Conceptual Space Relational Inference

November 6, 2022

Measurement-Consistent Networks via a Deep Implicit Layer for Solving Inverse Problems
Rahul Mourya, João F. C. Mota
Deep Neural Network Inverse Problem DNN Framework Single Image Super Resolution Deep Equilibrium Scale Consistent Network

October 16, 2022

Stability of Accuracy for the Training of DNNs Via the Uniform Doubling Condition
Yitzchak Shmalo
Deep Neural Network Training Data Core Stability Cross Entropy Loss DNN Framework

October 14, 2022

InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
Mingfu Xue, Xin Wang, Yinghao Wu, Shifeng Ni, Yushu Zhang, Weiqiang Liu
Deep Neural Network DNN Framework DNN Model Intellectual Property Protection Intellectual Property Intrinsic Feature

October 8, 2022

Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization
Yao Lu, Jide Zhang, Su Zheng, Zhen Li, Lingli Wang
DNN Framework Co Design Low Priority Neural Network Weight DNN Accuracy Class Wise Multiplier Approximate Multiplier

September 21, 2022

Progressive with Purpose: Guiding Progressive Inpainting DNNs through Context and Structure
Kangdi Shi, Muhammad Alrabeiah, Jun Chen
Context Information Inner Structure DNN Framework Image Feature Left Leaning Context Feature Convolutional Encoder Laplacian Pyramid Image Frequency

September 18, 2022

Improving the Performance of DNN-based Software Services using Automated Layer Caching
Mohammadamin Abedi, Yanni Iouannou, Pooyan Jamshidi, Hadi Hemmati
Deep Neural Network System Performance DNN Framework DNN Model Software System Optimization Layer

DNN Framework

Papers

Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds

Does a Neural Network Really Encode Symbolic Concepts?

Practical Knowledge Distillation: Using DNNs to Beat DNNs

A DNN based Normalized Time-frequency Weighted Criterion for Robust Wideband DoA Estimation

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

NeuRI: Diversifying DNN Generation via Inductive Rule Inference

DynaMIX: Resource Optimization for DNN-Based Real-Time Applications on a Multi-Tasking System

The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks

Efficient Evaluation Methods for Neural Architecture Search: A Survey

ExcelFormer: Can a DNN be a Sure Bet for Tabular Prediction?

Higher order organizational features can distinguish protein interaction networks of disease classes: a case study of neoplasms and neurological diseases

Adversarial Example Defense via Perturbation Grading Strategy

Efficiently Finding Adversarial Examples with DNN Preprocessing

Emergence of Concepts in DNNs?

Measurement-Consistent Networks via a Deep Implicit Layer for Solving Inverse Problems

Stability of Accuracy for the Training of DNNs Via the Uniform Doubling Condition

InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features

Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization

Progressive with Purpose: Guiding Progressive Inpainting DNNs through Context and Structure

Improving the Performance of DNN-based Software Services using Automated Layer Caching