Results 161 to 170 of about 14,957 (259)

Thermodynamics à la Souriau on Kähler Non-Compact Symmetric Spaces for Cartan Neural Networks. [PDF]

Entropy (Basel)
Fré PG, Sorin AS, Trigiante M.
europepmc   +1 more source

Tandem Neural Network Rapidly Solves Multivalued Inverse Problems: Application to Oxide‐Semiconductor Characterization

Advanced Intelligent Systems, EarlyView.
A tandem neural network directly solves the multivalued inverse problem of extracting semiconductor parameters from transistor measurements. Trained on only 1000 simulations, the network infers six material parameters (e.g., defect states, carrier concentration, mobility) in under 1 ms, demonstrating a broadly applicable framework for semiconductor ...
Masatoshi Kimura, Keisuke Ide, Kuan‐Ju Zhou, Atsushi Shimizu, Takayoshi Katase, Hidenori Hiramatsu, Kei Terayama, Hideo Hosono, Toshio Kamiya   +8 more
wiley   +1 more source

Precise Time Synchronization in Packet Networks Using Deep Learning for Future Intelligent Transportation. [PDF]

Sensors (Basel)
Deng H, Li H, Tian Z, Tian J, Du W.
europepmc   +1 more source

Integrating Reinforcement Learning With Explainable Artificial Intelligence for Real‐Time Clinical Decision Support in Dynamic Healthcare Environments

Advanced Intelligent Systems, EarlyView.
A hybrid Reinforcement Learning–Explainable AI framework integrates SHAP and LIME explanations directly into a Deep Q‐Network inference loop for real‐time ICU decision support. Trained on 18 142 mechanically ventilated stays from the eICU database, the system attains 93.0% decision accuracy, 20% fewer errors than RL alone, and a 91% clinician trust ...
Jannatul Ferdaus Disha, MD Faiaz Zaman Dehan, Kazi Md. Tanvir Anzum   +2 more
wiley   +1 more source

A shared frailty model for assessing time to seizure remission in adults with epilepsy. [PDF]

Sci Rep
Jote AD, Lelisho ME, Sheferaw WE.
europepmc   +1 more source

Balancing Exploration and Exploitation Through a Sequential Hybrid of Roach Infestation and Mayfly Algorithms for Constrained Engineering Design Optimization

AI &Innovation, EarlyView.
ABSTRACT Maintaining an effective balance between exploration and exploitation is essential during optimization processes, from mathematical functions to more complex problems such as constrained engineering design optimization, particularly when addressing highly nonlinear issues with numerous local optima and strict feasibility requirements.
Enrique Lizárraga, Fevrier Valdez, Oscar Castillo, Patricia Melin   +3 more
wiley   +1 more source

A Proposal for Homoskedastic Modeling With Conditional Auto-Regressive Distributions. [PDF]

Stat Med
Martinez-Beneito MA, Adin A, Goicoa T, Dolores Ugarte M.   +3 more
europepmc   +1 more source

Input Layer Regularization and Automated Regularization Hyperparameter Tuning for Myelin Water Estimation Using Deep Learning. [PDF]

NMR Biomed
Modi M, Sule S, Palumbo J, Rozowski M, Hampton GS, Bouhrara M, Czaja W, Spencer RG.   +7 more
europepmc   +1 more source

Childhood underweight in Ethiopia: modelling non-linear risk factors and geographic hotspots using Bayesian geoadditive methods. [PDF]

Front Public Health
Derso EA, Campolo MG, Alibrandi A.
europepmc   +1 more source

Accelerating Sustainable Epoxy Resin Development Through Bayesian Optimization and Inverse Design

Journal of Applied Polymer Science, EarlyView.
Development of a machine learning framework for the optimization of the Tg of partially bio‐based epoxy resin formulations in a 13‐component design space using Bayesian optimization, active learning, random design, and inverse design. The results show that the BO effectively navigates high‐dimensional formulation spaces, and the final ML model could ...
Natalie Wunder, Rodrigo Q. Albuquerque, Florian Max, Holger Ruckdäschel   +3 more
wiley   +1 more source