Deep Neural Network

Deep neural networks (DNNs) are complex computational models aiming to mimic the human brain's learning capabilities, primarily focusing on achieving high accuracy and efficiency in various tasks. Current research emphasizes understanding DNN training dynamics, including phenomena like neural collapse and the impact of architectural choices (e.g., convolutional, transformer, and operator networks) and training strategies (e.g., weight decay, knowledge distillation, active learning). This understanding is crucial for improving DNN performance, robustness (including against adversarial attacks and noisy data), and resource efficiency in diverse applications ranging from image recognition and natural language processing to scientific modeling and edge computing.

2129papers

Papers - Page 16

September 9, 2024

Predicting Critical Heat Flux with Uncertainty Quantification and Domain Generalization Using Conditional Variational Autoencoders and Deep Neural Networks
Farah Alsafadi, Aidan Furlong, Xu Wu
Conditional Variational Conditional Variational Autoencoder Uncertainty Quantification Deep Neural Network Synthetic Dataset Domain Generalization

September 8, 2024

HYDRA: Hybrid Data Multiplexing and Run-time Layer Configurable DNN Accelerator
Sonu Kumar, Komal Gupta, Gopal Raut, Mukul Lokhande, Santosh Kumar Vishvakarma
Data Multiplexing Multi Layer Deep Neural Network Edge Device Hydra MDP

September 7, 2024

Metadata augmented deep neural networks for wild animal classification
Aslak Tøn, Ammar Ahmed, Ali Shariq Imran, Mohib Ullah, R. Muhammad Atif Azad
Wildlife Monitoring Software Classification Metadata Information Deep Neural Network

September 6, 2024

September 5, 2024

September 3, 2024

September 2, 2024

September 1, 2024

August 31, 2024

Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
Hanyang Wang, Hao Zhou, Sibo Cheng
Voronoi Tessellation Spatio Temporal Prediction Dynamic Prediction Deep Neural Network Spatio Temporal Physical Constraint

August 30, 2024

Deep Neural Network

Papers - Page 16

Predicting Critical Heat Flux with Uncertainty Quantification and Domain Generalization Using Conditional Variational Autoencoders and Deep Neural Networks

HYDRA: Hybrid Data Multiplexing and Run-time Layer Configurable DNN Accelerator

Metadata augmented deep neural networks for wild animal classification

The Impact of Scanner Domain Shift on Deep Learning Performance in Medical Imaging: an Experimental Study

Towards Narrowing the Generalization Gap in Deep Boolean Networks

WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking

FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks

UnLearning from Experience to Avoid Spurious Correlations

ForeCal: Random Forest-based Calibration for DNNs

Adaptive Class Emergence Training: Enhancing Neural Network Stability and Generalization through Progressive Target Evolution

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

Convolutional Networks as Extremely Small Foundation Models: Visual Prompting and Theoretical Perspective

Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data

CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads

DNN-GDITD: Out-of-distribution detection via Deep Neural Network based Gaussian Descriptor for Imbalanced Tabular Data

Trust And Balance: Few Trusted Samples Pseudo-Labeling and Temperature Scaled Loss for Effective Source-Free Unsupervised Domain Adaptation

Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment

Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint

Deep Neural Networks for Predicting Recurrence and Survival in Patients with Esophageal Cancer After Surgery

Deep Feature Embedding for Tabular Data