Results 151 to 160 of about 15,152,665 (258)

A NEAT Approach to Evolving Neural‐Network‐Based Optimization of Chiral Photonic Metasurfaces: Application of a NeuroEvolution‐of‐Augmenting‐Topologies Pipeline

Advanced Intelligent Systems, EarlyView.
Neuro‐evolution can boost machine‐learning optimization of chiral metasurfaces. By integrating the NEAT algorithm into a deep‐learning framework, we enable the efficient design of visible‐spectrum chiroptical responses. NEAT autonomously evolves neural‐network architectures and weights, reducing manual tuning.
Davide Filippozzi, Arash Rahimi‐Iman
wiley   +1 more source

Artificial Intelligence-Based Decision Support System for UAV Control in a Simulated Environment. [PDF]

Sensors (Basel)
Sujecki P, Frąszczak D.
europepmc   +1 more source

Energy‐Aware Perturbation Optimization for Memristor‐Array Convolutional Neural Networks

Advanced Intelligent Systems, EarlyView.
Memristor‐array inference becomes more energy efficient when layer inputs are reshaped before computation. Sinusoidal perturbation encoding with dual‐threshold screening reduces active voltage pulses and contracts ADC input‐current ranges, jointly lowering crossbar and peripheral energy while preserving accuracy across hardware MNIST validation, deep ...
Ao Xu, Lun Lu, Youpeng Wu, Yao Guo, Yi Li, Yinan Wang, Qingjiang Li   +6 more
wiley   +1 more source

Safe and adaptive control of non-stationary stochastic systems via Lyapunov-constrained distributional reinforcement learning. [PDF]

Sci Rep
Khaniki MAL, Mirzaee M, Moradi E.
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

Deep Learning-Based Intelligent Resource Management for Renewable Energy Engineering Projects. [PDF]

Ann N Y Acad Sci
Yao Y.
europepmc   +1 more source

Stochastic Locomotion Emerging From Body–Environment Interactions in a Mexican Jumping Bean–Inspired Robot

Advanced Intelligent Systems, EarlyView.
Inspired by the Mexican jumping bean, this study presents a centimeter‐scale, electronics‐free robot that merges principles from both the animal and plant kingdoms. A thermo‐responsive actuator mimicking larval motion, enclosed within a uniquely shaped plant‐seed‐inspired shell, generates jumping, rolling, flipping, sliding, and climbing through ...
Ragesh Chellattoan, Alessio Mondini, Edoardo Sinibaldi, Barbara Mazzolai   +3 more
wiley   +1 more source

Speed Control of Single Molecules on a Surface

Angewandte Chemie, EarlyView.
The speed of a single molecule moving across a silver crystal surface is determined with the tip of a scanning tunneling microscope (STM). Travelling distances Δx and travelling times Δt, which are determined simultaneously with high precision, allow to directly measure time–distance relationships.
Donato Civita, Matthew J. Timm, Julia Lanz, Christophe Nacci, Stefan Hecht, Leonhard Grill   +5 more
wiley   +2 more sources

Object-centric diffusion policies for real-world robotic-arm imitation learning. [PDF]

Front Robot AI
Kasu PR, Um D.
europepmc   +1 more source

Exploiting Edge Semantics in Job Shop Scheduling Problem With Heterogeneous Graph Transformers

Advanced Intelligent Systems, EarlyView.
A heterogeneous graph transformer (HGT) is introduced for reinforcement learning‐based job shop scheduling by explicitly distinguishing precedence and machine‐contention relations through edge‐type‐specific attention. The proposed framework learns richer scheduling representations, improves decision quality over homogeneous graph models, and highlights
Bulent Soykan, Fatih Kasimoglu
wiley   +1 more source