Results 151 to 160 of about 544,487 (316)

Advances in Reinforcement Learning

, 2011
no ...
openaire   +4 more sources

Why Reinforcement Learning?

Algorithms
The term Artificial Intelligence (AI) has come to be one of the most frequently expressed keywords around the globe [...]
Mehmet Emin Aydin, Rafet Durgut, Abdur Rakib   +2 more
doaj   +1 more source

Learning and the reinforcement principle [PDF]

, 1973
W. T. Lippincott
openalex   +1 more source

Biological and Mechanical Limitations for Chronic Fast‐Scan Cyclic Voltammetry Sensor Design

Advanced Materials Technologies, EarlyView.
Real‐time detection of neurochemicals has demonstrated value in the field of neuroscience. However, current methods have limitations for use in the chronic setting, which is often the ideal environment for research. This article discusses these limitations, as well as technologies that have been developed to overcome them, and provides recommendations ...
Mason L. Perillo, Bhavna Gupta, Akash Saxena, Alexandra P. Veltri, Wen Li, James R. Siegenthaler, Erin K. Purcell   +6 more
wiley   +1 more source

Self‐Folded Corrugated Origami Sensor Based on Triboelectric Nanogenerator for a Smart Cushioning Device

Advanced Materials Technologies, EarlyView.
A corrugated origami TENG (CO‐TENG) soft sensor utilizes paper self‐folding technology to create battery‐free devices by laminating and folding sheet materials. In the object drop test, the voltage generated by CO‐TENG is classified with machine learning to achieve an accuracy of 98.9%, which shows its potential for smart cushioning devices.
Haruki Higoshi, Daichi Naritomi, Shota Kamiyauchi, Hiroaki Minamide, Keisuke Yamashita, Satoshi Ueno, Yuki Fukatsu, Kotaro Nakane, Hiroki Shigemune   +8 more
wiley   +1 more source

Research Progress on Atmospheric Turbulence Perception and Correction Based on Adaptive Optics and Deep Learning

Advanced Photonics Research, EarlyView.
This work presents a systematic review of atmospheric turbulence fundamentals, including theoretical formulations and adaptive optics‐based mitigation strategies. This includes an in‐depth examination of the devices, theories, and methodologies associated with traditional correction approaches.
Qinghui Liu, Yihang Di, Mengmeng Zhang, Zhenbo Ren, Jianglei Di, Jianlin Zhao   +5 more
wiley   +1 more source

ERRORLESS LEARNING: REINFORCEMENT CONTINGENCIES AND STIMULUS CONTROL TRANSFER IN DELAYED PROMPTING [PDF]

, 1984
Paul E. Touchette, Jane S. Howard
openalex   +1 more source

A Meta‐Model for The Design of Soft Pneumatic Actuators Using Neural Networks and Finite Element Analysis

Advanced Theory and Simulations, EarlyView.
Data is generated from finite element simulations and an encoding using a Moore domain. The data is then used to train a meta‐model to predict the soft unit's deformation state depending on its chamber shape and properties as well as the surrounding environment.
Philip Frederik Ligthart, Martin Philip Venter   +1 more
wiley   +1 more source

Response sequence learning as a function of primary versus conditioned reinforcement [PDF]

, 1988
S. J. Luck, Marianne Colgrove, Allen Neuringer   +2 more
openalex   +1 more source

Genome‐Wide Silencer Screening Reveals Key Silencer Modulating Reprogramming Efficiency in Mouse Induced Pluripotent Stem Cells

Advanced Science, EarlyView.
This study utilized Ss‐STARR‐seq to construct a genome‐wide silencer map of mouse cells and elucidated the fundamental characteristics of these silencers. These silencers exist in a cell‐specific manner and exhibit unique epigenetic modifications. Through functional experiments, we also discovered that these silencers can regulate gene expression and ...
Xiusheng Zhu, Lei Huang, Guoli Li, Biao Deng, Xiaoxiao Wang, Hu Yang, Yuanyuan Zhang, Qiuhan Wen, Chao Wang, Jingshu Zhang, Yunxiang Zhao, Kui Li, Yuwen Liu   +12 more
wiley   +1 more source