Deep Learning
Deep learning, a subfield of machine learning, focuses on training artificial neural networks with multiple layers to extract complex patterns from data. Current research emphasizes improving model robustness against noisy or adversarial inputs, exploring efficient architectures like Vision Transformers and convolutional LSTMs for various tasks (e.g., image classification, time series forecasting), and integrating physics-informed approaches for enhanced interpretability and reliability. These advancements are significantly impacting diverse fields, from automated industrial inspection and medical image analysis to improved weather forecasting and more efficient content moderation systems.
Papers
Symbolic-AI-Fusion Deep Learning (SAIF-DL): Encoding Knowledge into Training with Answer Set Programming Loss Penalties by a Novel Loss Function Approach
Fadi Al Machot, Martin Thomas Horsch, Habib Ullah
DEEGITS: Deep Learning based Framework for Measuring Heterogenous Traffic State in Challenging Traffic Scenarios
Muttahirul Islam, Nazmul Haque, Md. Hadiuzzaman
Fault Localization in Deep Learning-based Software: A System-level Approach
Mohammad Mehdi Morovati, Amin Nikanjam, Foutse Khomh
EAPCR: A Universal Feature Extractor for Scientific Data without Explicit Feature Relation Patterns
Zhuohang Yu, Ling An, Yansong Li, Yu Wu, Zeyu Dong, Zhangdi Liu, Le Gao, Zhenyu Zhang, Chichun Zhou
Deep Learning 2.0: Artificial Neurons That Matter -- Reject Correlation, Embrace Orthogonality
Taha Bouhsine
Towards Vision Mixture of Experts for Wildlife Monitoring on the Edge
Emmanuel Azuh Mensah, Anderson Lee, Haoran Zhang, Yitong Shan, Kurtis Heimerl
Maritime Search and Rescue Missions with Aerial Images: A Survey
Juan P. Martinez-Esteso, Francisco J. Castellanos, Jorge Calvo-Zaragoza, Antonio Javier Gallego
Semantic segmentation on multi-resolution optical and microwave data using deep learning
Jai G Singla, Bakul Vaghela
EUR/USD Exchange Rate Forecasting incorporating Text Mining Based on Pre-trained Language Models and Deep Learning Methods
Xiangyu Shi, Hongcheng Ding, Salaar Faroog, Deshinta Arrova Dewi, Shamsul Nahar Abdullah, Bahiah A Malek
AdaS&S: a One-Shot Supernet Approach for Automatic Embedding Size Search in Deep Recommender System
He Wei, Yuekui Yang, Yang Zhang, Haiyang Wu, Meixi Liu, Shaoping Ma
Increasing Rosacea Awareness Among Population Using Deep Learning and Statistical Approaches
Chengyu Yang, Chengjun Liu
Permutative redundancy and uncertainty of the objective in deep learning
Vacslav Glukhov
Classification of residential and non-residential buildings based on satellite data using deep learning
Jai G Singla
Methane projections from Canada's oil sands tailings using scientific deep learning reveal significant underestimation
Esha Saha, Oscar Wang, Amit K. Chakraborty, Pablo Venegas Garcia, Russell Milne, Hao Wang
A method based on Generative Adversarial Networks for disentangling physical and chemical properties of stars in astronomical spectra
Raúl Santoveña, Carlos Dafonte, Minia Manteiga
FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information
Shreen Gul, Mohamed Elmahallawy, Sanjay Madria, Ardhendu Tripathy
Do Histopathological Foundation Models Eliminate Batch Effects? A Comparative Study
Jonah Kömen, Hannah Marienwald, Jonas Dippel, Julius Hense