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.
Papers - Page 20
Evaluating Deep Neural Networks in Deployment (A Comparative and Replicability Study)
Causal inference through multi-stage learning and doubly robust deep neural networks
Graph Expansions of Deep Neural Networks and their Universal Scaling Limits
Using deep neural networks to detect non-analytically defined expert event labels in canoe sprint force sensor signals
SwishReLU: A Unified Approach to Activation Functions for Enhanced Deep Neural Networks Performance