Results 71 to 80 of about 2,128 (206)

Enhancing Neural Network Training Through Neuroevolutionary Models: A Hybrid Approach to Classification Optimization

Mathematics
The optimization of Artificial Neural Networks (ANNs) remains a significant challenge in machine learning, particularly in overcoming local-optima limitations during training.
Hyasseliny A. Hurtado-Mora, Luis A. Herrera-Barajas, Luis J. González-del-Ángel, Roberto Pichardo-Ramírez, Alejandro H. García-Ruiz, Katea E. Lira-García   +5 more
doaj   +1 more source

Psycholinguistics and the Search for Extraterrestrial Intelligence [PDF]

Философия и космология, 2017
The author of the article reveals the possibilities of psycholinguistics in the identifi cation and interpretation of languages and texts of Alien Civilizations.
Lidija Krotenko
doaj  

Machine Learning Potential for Ga–In Alloy Melting

Materials Genome Engineering Advances, Volume 4, Issue 3, August 2026.
Liquid metals are essential for flexible electronics and soft robotics, yet their melting behavior remains difficult to predict. This work benchmarks machine‐learning potentials and introduces a local Lindemann approach for melting‐temperature calculations in disordered alloys, enabling realistic large‐scale simulations and advancing liquid‐metal ...
Chen Hua, Jing Liu
wiley   +1 more source

Learning What Information Matters and When: Concurrent Input Selection and Policy Optimization in Multipurpose Reservoir Operations

Water Resources Research, Volume 62, Issue 7, July 2026.
Abstract Managing multi‐purpose reservoirs requires balancing flood protection, water supply, and ecosystem needs under growing uncertainty. A critical challenge is deciding what information to use and when: forecasts exist across multiple variables and lead times, yet their operational value depends on both the management objectives and the policy ...
Davide Spinelli, Marta Zaniolo, Matteo Giuliani, Andrea Castelletti   +3 more
wiley   +1 more source

Modular neuroevolution for multilegged locomotion [PDF]

Proceedings of the 10th annual conference on Genetic and evolutionary computation, 2008
Legged robots are useful in tasks such as search and rescue because they can effectively navigate on rugged terrain. However, it is difficult to design controllers for them that would be stable and robust. Learning the control behavior is difficult because optimal behavior is not known, and the search space is too large for reinforcement learning and ...
Vinod K. Valsalam, Risto Miikkulainen
openaire   +2 more sources

Neuroevolution of recurrent architectures on control tasks

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2022
Modern artificial intelligence works typically train the parameters of fixed-sized deep neural networks using gradient-based optimization techniques. Simple evolutionary algorithms have recently been shown to also be capable of optimizing deep neural network parameters, at times matching the performance of gradient-based techniques, e.g.
Maximilien Le Clei, Pierre Bellec
openaire   +3 more sources

Multimodal Actuation and Environment Adaptive Strategies of Bio‐Inspired Micro/Nanorobots in Precision Medicine

Advanced Robotics Research, Volume 2, Issue 3, June 2026.
An introduction for multidrive and environment‐adaptive micro/nanorobotics: design and fabrication strategies, intelligent actuation, and their applications. Various intelligent actuation approaches—magnetic, acoustic, optical, chemical, and biological—can be synergistically designed to enhance flexibility and adaptive behavior for precision medicine ...
Aiqing Ma, Han Gong, Jiacheng Ouyang, Liqi Chen, Tianfang Kang, Yiran He, Guojun Huang, Sidi Zheng, Ting Yin, Hong Pan, Lintao Cai   +10 more
wiley   +1 more source

Ensembles of Biologically Inspired Optimization Algorithms for Training Multilayer Perceptron Neural Networks

Applied Sciences, 2022
Artificial neural networks have proven to be effective in a wide range of fields, providing solutions to various problems. Training artificial neural networks using evolutionary algorithms is known as neuroevolution.
Sabina-Adriana Floria, Marius Gavrilescu, Florin Leon, Silvia Curteanu   +3 more
doaj   +1 more source

GPUMDkit: A User‐Friendly Toolkit for GPUMD and NEP

Materials Genome Engineering Advances, Volume 4, Issue 2, June 2026.
GPUMDkit is a comprehensive and user‐friendly toolkit for GPUMD and NEP programs, integrating format conversion, structure sampling, property calculation, and visualization into a unified interface, substantially lowering the barrier to entry for machine‐learning molecular dynamics simulations with GPUMD and NEP.
Zihan Yan, Denan Li, Xin Wu, Zhoulin Liu, Chen Hua, Boyi Situ, Hao Yang, Shengjie Tang, Benrui Tang, Ziyang Wang, Shangzhao Yi, Huan Wang, Dian Huang, Ke Li, Qilin Guo, Zherui Chen, Ke Xu, Yanzhou Wang, Ziliang Wang, Gang Tang, Shi Liu, Zheyong Fan, Yizhou Zhu   +22 more
wiley   +1 more source

AI‐Organized Multiscale Battery Modeling: Linking Structure and Property from Quantum to Device Scales

Small Structures, Volume 7, Issue 6, June 2026.
Multiscale modeling of battery systems combines quantum‐mechanical calculations, atomistic simulations, and mesoscale phase‐field approaches to describe processes spanning from reaction energetics to morphology evolution. Establishing consistent links between these scales remains a key challenge, particularly for the transfer of physical descriptors ...
Shoutong Jin, Ziyuan Wang, Mengke Li, Zeyu Deng   +3 more
wiley   +1 more source