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

April 8, 2024

Lightweight Inference for Forward-Forward Algorithm
Amin Aminifar, Baichuan Huang, Azra Abtahi, Amir Aminifar
Deep Neural Network Back Propagation DNN Framework Forward Forward Algorithm MNIST Canadian Institute for Advanced

March 30, 2024

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
Renyang Liu, Kwok-Yan Lam, Wei Zhou, Sixing Wu, Jun Zhao, Dongting Hu, Mingming Gong
Native Robustness Adversarial Example Adversarial Training DNN Framework Black Box Attack

March 23, 2024

Carbon Intensity-Aware Adaptive Inference of DNNs
Jiwan Jung
DNN Framework Accurate Model DNN Inference Carbon Emission Adaptive Inference Carbon Figure

March 18, 2024

Normalized Validity Scores for DNNs in Regression based Eye Feature Extraction
Wolfgang Fuhl
Novel Regression DNN Framework Eye View Landmark Detection Iris Segmentation Construct Validity Semantic Landmark Detection

March 14, 2024

Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environment
Atah Nuh Mih, Alireza Rahimi, Asfia Kawnine, Francis Palma, Monica Wachowicz, Rickey Dubay, Hung Cao
Deep Neural Network DNN Framework Pareto Optimal Device Training Resource Constrained Edge Memory Reduction Parameter Reduction

March 5, 2024

DNNLasso: Scalable Graph Learning for Matrix-Variate Data
Meixia Lin, Yangjing Zhang
Graph Learning DNN Framework Kronecker Product Precision Matrix Graphical Lasso Matrix Variate

February 29, 2024

SoD$^2$: Statically Optimizing Dynamic Deep Neural Network
Wei Niu, Gagan Agrawal, Bin Ren
Code Generation DNN Framework Static Deep Neural Network Dynamic Deep Memory Allocation

February 9, 2024

Towards Fair and Firm Real-Time Scheduling in DNN Multi-Tenant Multi-Accelerator Systems via Reinforcement Learning
Enrico Russo, Francesco Giulio Blanco, Maurizio Palesi, Giuseppe Ascia, Davide Patti, Vincenzo Catania
Reinforcement Learning Deep Reinforcement Learning DNN Framework Quality of Service Multi Accelerator Real Time Scheduling

February 1, 2024

Control-Theoretic Techniques for Online Adaptation of Deep Neural Networks in Dynamical Systems
Jacob G. Elkins, Farbod Fahimi
Deep Neural Network Dynamical System DNN Framework Online Adaptation Fully Connected Deep Neural Network Parameter Control Theoretic DNN Prediction

January 30, 2024

SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget
Kun Wang, Jiani Cao, Zimu Zhou, Zhenjiang Li
Deep Neural Network DNN Framework Edge AI Efficient Deep Swap Distance Minimization DNN Inference Limited Memory Multi DNN Scheduling

January 29, 2024

Defining and Extracting generalizable interaction primitives from DNNs
Lu Chen, Siyu Lou, Benhao Huang, Quanshi Zhang
Deep Neural Network Explainable AI DNN Framework Generalization Capacity Action Primitive

December 11, 2023

Towards A Flexible Accuracy-Oriented Deep Learning Module Inference Latency Prediction Framework for Adaptive Optimization Algorithms
Jingran Shen, Nikos Tziritas, Georgios Theodoropoulos
Deep Learning Deep Neural Network DNN Framework Adaptive Optimization Method

December 10, 2023

Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computing
Luca Marzari, Gabriele Roncolato, Alessandro Farinelli
DNN Framework Reachability Analysis Formal Verification Parallel Processing Model Safety DNN Verification Bound Propagation DNN Verifier

December 5, 2023

REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training
Jiaxu Zhao, Lu Yin, Shiwei Liu, Meng Fang, Mykola Pechenizkiy
Deep Neural Network DNN Framework Sparse Training Group Robustness Biased Data Rest RESTAD NAP Bias Attribute

December 4, 2023

Signed Binarization: Unlocking Efficiency Through Repetition-Sparsity Trade-Off
Sachit Kuhar, Yash Jain, Alexey Tumanov
Deep Neural Network DNN Framework Efficient Inference Binarization Method Enhancing Efficiency Partial Binarization

November 29, 2023

Adaptive Early Exiting for Collaborative Inference over Noisy Wireless Channels
Mikolaj Jankowski, Deniz Gunduz, Krystian Mikolajczyk
Deep Neural Network Adaptive Importance DNN Framework Collaborative Inference Early eXit Wireless Edge Noisy Channel

November 13, 2023

Mitigating Backdoors within Deep Neural Networks in Data-limited Configuration
Soroush Hashemifar, Saeed Parsa, Morteza Zakeri-Nasrabadi
Deep Neural Network DNN Framework Limited Data Mitigating Backdoor Backdoor Policy

November 7, 2023

AGNES: Abstraction-guided Framework for Deep Neural Networks Security
Akshay Dhonthi, Marcello Eiermann, Ernst Moritz Hahn, Vahid Hashemi
Deep Neural Network Autonomous Driving Backdoor Attack DNN Framework Image Recognition Abstraction Based

October 17, 2023

Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs
Uri Stern, Daphna Weinshall
Deep Neural Network Anti Forgetting Deep Model DNN Framework Training Free Model Overfitting Modern Deep Learning Model

September 26, 2023

Fixing the problems of deep neural networks will require better training data and learning algorithms
Drew Linsley, Thomas Serre
Deep Neural Network Training Data Real Human DNN Framework Learning Algorithm Related Problem Biological Vision Human Accuracy Low Quality Model