Deep Learning Model
Deep learning models are complex computational systems designed to learn patterns from data, achieving high accuracy in various tasks like image classification, natural language processing, and time series forecasting. Current research emphasizes improving model efficiency (e.g., through parameter reduction and optimized training algorithms), robustness (e.g., against adversarial attacks and noisy data), and interpretability (e.g., via feature attribution and visualization techniques), often employing architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs, including LSTMs and GRUs), and transformers. These advancements are driving significant impact across diverse fields, from medical diagnosis and environmental monitoring to industrial automation and personalized medicine.
Papers
Transformer models as an efficient replacement for statistical test suites to evaluate the quality of random numbers
Rishabh Goel, YiZi Xiao, Ramin Ramezani
Is ReLU Adversarially Robust?
Korn Sooksatra, Greg Hamerly, Pablo Rivas
Research on Image Recognition Technology Based on Multimodal Deep Learning
Jinyin Wang, Xingchen Li, Yixuan Jin, Yihao Zhong, Keke Zhang, Chang Zhou
Interpretable Vital Sign Forecasting with Model Agnostic Attention Maps
Yuwei Liu, Chen Dan, Anubhav Bhatti, Bingjie Shen, Divij Gupta, Suraj Parmar, San Lee
Key Patches Are All You Need: A Multiple Instance Learning Framework For Robust Medical Diagnosis
Diogo J. Araújo, M. Rita Verdelho, Alceu Bissoto, Jacinto C. Nascimento, Carlos Santiago, Catarina Barata
The Importance of Model Inspection for Better Understanding Performance Characteristics of Graph Neural Networks
Nairouz Shehata, Carolina Piçarra, Anees Kazi, Ben Glocker
Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
Aditya Chakravarty
KAN: Kolmogorov-Arnold Networks
Ziming Liu, Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Soljačić, Thomas Y. Hou, Max Tegmark
Enhancing Deep Learning Model Explainability in Brain Tumor Datasets using Post-Heuristic Approaches
Konstantinos Pasvantis, Eftychios Protopapadakis
Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs
Soham Mitra, Atri Sukul, Swalpa Kumar Roy, Pravendra Singh, Vinay Verma
Generalization capabilities and robustness of hybrid machine learning models grounded in flow physics compared to purely deep learning models
Rodrigo Abadía-Heredia, Adrián Corrochano, Manuel Lopez-Martin, Soledad Le Clainche
Personalized Federated Learning via Sequential Layer Expansion in Representation Learning
Jaewon Jang, Bonjun Choi