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

April 11, 2024

Automatic Detection of Dark Ship-to-Ship Transfers using Deep Learning and Satellite Imagery
Ollie Ballinger
Deep Learning Black Box Automatic Detection Satellite Imagery Ship Detection Satellite Detection
A lightweight dual-stage framework for personalized speech enhancement based on DeepFilterNet2
Thomas Serre, Mathieu Fontaine, Éric Benhaim, Geoffroy Dutour, Slim Essid
Deep Learning Speaker Embeddings Dual Stage Speech Enhancement Network Personalized Speech Enhancement
Adversarial Robustness of Distilled and Pruned Deep Learning-based Wireless Classifiers
Nayan Moni Baishya, B. R. Manoj
Deep Learning Adversarial Attack Adversarial Robustness Better Robustness Signal Classification Automatic Modulation Classification Efficient Adversarial Training
Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis
Nayan Moni Baishya, B. R. Manoj, Prabin K. Bora
Deep Learning Convolutional Neural Network Edge Device Performance Analysis Learning Benchmark Automatic Modulation Classification

April 9, 2024

Deep Learning Method for Computing Committor Functions with Adaptive Sampling
Bo Lin, Weiqing Ren
Deep Learning High Dimensional Adaptive Sampling Complex System Metastable State Committor Function
(Not) Understanding Latin Poetic Style with Deep Learning
Ben Nagy
Deep Learning Better Interpretability Latin Text Learned Embeddings Authorship Analysis Writing Style
Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey
Feng Liang, Zhen Zhang, Haifeng Lu, Victor C. M. Leung, Yanyi Guo, Xiping Hu
Deep Learning Comprehensive Survey Potential Scalability Communication Efficient Communication Efficiency
Unifying Low Dimensional Observations in Deep Learning Through the Deep Linear Unconstrained Feature Model
Connall Garrod, Jonathan P. Keating
Deep Learning High Dimensional Neural Collapse Deep Linear Low Dimensional Structure Unconstrained Feature Model

April 8, 2024

Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning
Fabian Perez, Jhon Lopez, Henry Arguello
Deep Learning Deep Learning System Privacy Preservation Image Encryption Deformable Transformation
DRoP: Distributionally Robust Pruning
Artem Vysogorets, Kartik Ahuja, Julia Kempe
Deep Learning Implicit Bias Data Pruning Biased Classifier Robust Pruning
Lightweight Deep Learning for Resource-Constrained Environments: A Survey
Hou-I Liu, Marco Galindo, Hongxia Xie, Lai-Kuan Wong, Hong-Han Shuai, Yung-Hui Li, Wen-Huang Cheng
Deep Learning Timely Survey TinyML Model Resource Constrained Low Power Lightweight Model Lightweight Deep
Convergence analysis of controlled particle systems arising in deep learning: from finite to infinite sample size
Huafu Liao, Alpár R. Mészáros, Chenchen Mou, Chao Zhou
Deep Learning Optimal Control Convergence Analysis Neural SDEs Sample Size Particle System Hamilton Jacobi Bellman Finite Data
Image-based Agarwood Resinous Area Segmentation using Deep Learning
Irwandi Hipiny, Johari Abdullah, Noor Alamshah Bolhassan
Deep Learning Image Segmentation Tree Specie Initial Segmentation
Importance of realism in procedurally-generated synthetic images for deep learning: case studies in maize and canola
Nazifa Azam Khan, Mikolaj Cieslak, Ian McQuillan
Deep Learning Synthetic Image Real Image Procedural Model Maize Plant Plant Growth Simulation

April 7, 2024

Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning
Aurélie Beaufrère, Nora Ouzir, Paul Emile Zafar, Astrid Laurent-Bellue, Miguel Albuquerque, Gwladys Lubuela, Jules Grégory, Catherine Guettier, Kévin Mondet, Jean-Christophe Pesquet, Valérie Paradis
Deep Learning Tumor Segmentation Liver Tumor Biopsy Core Tumor Annotation
DL-EWF: Deep Learning Empowering Women's Fashion with Grounded-Segment-Anything Segmentation for Body Shape Classification
Fatemeh Asghari, Mohammad Reza Soheili, Faezeh Gholamrezaie
Deep Learning Segmentation Based Approach Segmentation Result Body Shape Fashion Domain Female Speaker
AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning
Yuqi Song, Rongzhi Dong, Lai Wei, Qin Li, Jianjun Hu
Deep Learning Crystal Structure Crystalline Material Structure Prediction Crystal Structure Prediction Distance Matrix

Deep Learning

Papers

Automatic Detection of Dark Ship-to-Ship Transfers using Deep Learning and Satellite Imagery

A lightweight dual-stage framework for personalized speech enhancement based on DeepFilterNet2

Adversarial Robustness of Distilled and Pruned Deep Learning-based Wireless Classifiers

Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis

Research on Detection of Floating Objects in River and Lake Based on AI Intelligent Image Recognition

Fairness Evolution in Continual Learning for Medical Imaging

An inclusive review on deep learning techniques and their scope in handwriting recognition

Deep Learning Method for Computing Committor Functions with Adaptive Sampling

(Not) Understanding Latin Poetic Style with Deep Learning

Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey

Unifying Low Dimensional Observations in Deep Learning Through the Deep Linear Unconstrained Feature Model

Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning

DRoP: Distributionally Robust Pruning

Lightweight Deep Learning for Resource-Constrained Environments: A Survey

Convergence analysis of controlled particle systems arising in deep learning: from finite to infinite sample size

Image-based Agarwood Resinous Area Segmentation using Deep Learning

Importance of realism in procedurally-generated synthetic images for deep learning: case studies in maize and canola

Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning

DL-EWF: Deep Learning Empowering Women's Fashion with Grounded-Segment-Anything Segmentation for Body Shape Classification

AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning