Results 51 to 60 of about 786,949 (131)

Learning Topology and Dynamics of Large Recurrent Neural Networks

, 2014
Large-scale recurrent networks have drawn increasing attention recently because of their capabilities in modeling a large variety of real-world phenomena and physical mechanisms.
He, Yuejia, She, Yiyuan, Wu, Dapeng
core   +1 more source

Investigation of a physical model-based machine-learning force field for BaZrO3 perovskite

Journal of Aeronautical Materials, 2023
Interatomic potential is a key component of large-scale atomic simulation of materials. For scientific problems in complex environments such as high temperature，high pressure and irradiation，the interactions between atoms are often very complex.
ZHAO Liang, NIU Hongwei, JING Yuhang
doaj   +1 more source

A reinforcement learning theory for homeostatic regulation [PDF]

, 2011
Reinforcement learning models address animal’s behavioral adaptation to its changing “external” environment, and are based on the assumption that Pavlovian, habitual and goal-directed responses seek to maximize reward acquisition.
Gutkin, B. S., Keramati, M.
core  

Predicting the thermodynamic stability of perovskite oxides using machine learning models

, 2018
Perovskite materials have become ubiquitous in many technologically relevant applications, ranging from catalysts in solid oxide fuel cells to light absorbing layers in solar photovoltaics.
Jacobs, Ryan, Li, Wei, Morgan, Dane
core   +1 more source

Dynamical stability and chaos in artificial neural network trajectories along training

Frontiers in Complex Systems
The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network’s prediction, when confronted with a learning task.
Kaloyan Danovski, Miguel C. Soriano, Lucas Lacasa   +2 more
doaj   +1 more source

From synaptic interactions to collective dynamics in random neuronal networks models: critical role of eigenvectors and transient behavior [PDF]

, 2018
The study of neuronal interactions is currently at the center of several neuroscience big collaborative projects (including the Human Connectome, the Blue Brain, the Brainome, etc.) which attempt to obtain a detailed map of the entire brain matrix. Under
Chialvo, Dante R., Gudowska-Nowak, Ewa, Nowak, Maciej A., Ochab, Jeremi K., Tarnowski, Wojciech   +4 more
core   +2 more sources

Polynomial Iterative Learning Control (ILC) Tracking Control Design for Uncertain Repetitive Continuous-Time Linear Systems Applied to an Active Suspension of a Car Seat

Mathematics
This paper addresses the issue of polynomial iterative learning tracking control (Poly-ILC) for continuous-time linear systems (LTI) operating repetitively.
Selma Ben Attia, Sultan Alzahrani, Saad Alhuwaimel, Salah Salhi, Houssem Eddine Ouerfelli   +4 more
doaj   +1 more source

An Intelligent Algorithm for USVs Collision Avoidance Based on Deep Reinforcement Learning Approach with Navigation Characteristics

Journal of Marine Science and Engineering, 2023
Many achievements toward unmanned surface vehicles have been made using artificial intelligence theory to assist the decisions of the navigator. In particular, there has been rapid development in autonomous collision avoidance techniques that employ the ...
Zhe Sun, Yunsheng Fan, Guofeng Wang
doaj   +1 more source

Learning a DFT-based sequence with reinforcement learning: a NAO implementation

Paladyn, 2012
The implementation of sequence learning in robotic platforms offers several challenges. Deciding when to stop one action and continue to the next requires a balance between stability of sensory information and, of course, the knowledge about what action ...
Durán Boris, Lee Gauss, Lowe Robert
doaj   +1 more source

Exploration and Exploitation of New Knowledge Emergence to Improve the Collective Intelligent Decision-Making Level of Web-of-Cells With Cyber-Physical-Social Systems Based on Complex Network Modeling

IEEE Access, 2018
Through exploration and exploitation of new knowledge emergence, the collective intelligent decision-making (CID) level of Web-of-Cells (WoC) proposed by ELECTRA will be dramatically improved.
Lefeng Cheng, Tao Yu
doaj   +1 more source