Results 121 to 130 of about 5,619,500 (318)

Clustering with Reinforcement Learning

, 2007
We show how a previously derived method of using reinforcement learning for supervised clustering of a data set can lead to a sub-optimal solution if the cluster prototypes are initialised to poor positions. We then develop three novel reward functions which show great promise in overcoming poor initialization. We illustrate the results on several data
Barbakh, Wesam, Fyfe, Colin
openaire   +2 more sources

Biosupercapacitors for Human‐Powered Electronics

Advanced Functional Materials, EarlyView.
Biosupercapacitors are emerging as biocompatible and integrative energy systems for next‐generation bioelectronics, offering rapid charge–discharge performance and mechanical adaptability. This review systematically categorizes their applications from external to organ‐level systems and highlights their multifunctional roles in sensing, actuation, and ...
Suhyeon Kim, Seungho Baek, Woojung Jung, Hayeon Bae, Junyoung Mun, Yong Ho Kim, Sunkook Kim, Jung Ho Kim   +7 more
wiley   +1 more source

Naturalistic reinforcement learning

Trends in Cognitive Sciences
Humans possess a remarkable ability to make decisions within real-world environments that are expansive, complex, and multidimensional. Human cognitive computational neuroscience has sought to exploit reinforcement learning (RL) as a framework within which to explain human decision-making, often focusing on constrained, artificial experimental tasks ...
Wise, Toby, Emery, Kara, Radulescu, Angela   +2 more
openaire   +2 more sources

Enhanced Switching Performance in Single‐Crystalline PbTiO3 Ferroelectric Memristors for Replicating Synaptic Plasticity

Advanced Functional Materials, EarlyView.
This study demonstrated single‐crystalline PbTiO3‐based memristors with atomically sharp interfaces, well‐ordered lattices, and minimal lattice mismatch. The devices exhibited an ON/OFF ratio exceeding 105, high stability, and rich resistance‐state modulation.
Haining Li, Zhiqiang Liao, Risa Kataoka, Md Sarker Shamim, Takeshi Kijima, Hiroyasu Yamahara, Hitoshi Tabata, Munetoshi Seki   +7 more
wiley   +1 more source

Unveiling Phonon Contributions to Thermal Conductivity and the Applicability of the Wiedemann—Franz Law in Ruthenium and Tungsten Thin Films

Advanced Functional Materials, EarlyView.
Thermal transport in Ru and W thin films is studied using steady‐state thermoreflectance, ultrafast pump–probe spectroscopy, infrared‐visible spectroscopy, and computations. Significant Lorenz number deviations reveal strong phonon contributions, reaching 45% in Ru and 62% in W.
Md. Rafiqul Islam, Pravin Karna, Niraj Bhatt, Sandip Thakur, Helge Heinrich, Daniel M. Hirt, Saman Zare, Christopher Jezewski, Rinus T.P. Lee, Kandabara Tapily, John T. Gaskins, Colin D. Landon, Sean W. King, Ashutosh Giri, Patrick E. Hopkins   +14 more
wiley   +1 more source

Steep‐Switching Memory FET for Noise‐Resistant Reservoir Computing System

Advanced Functional Materials, EarlyView.
We demonstrate the steep‐switching memory FET with CuInP2S6/h‐BN/α‐In2Se3 heterostructure for application in noise‐resistant reservoir computing systems. The proposed device achieves steep switching characteristics (SSPGM = 19 mV/dec and SSERS = 23 mV/dec) through stabilization between CuInP2S6 and h‐BN.
Seongkweon Kang, Jaerok Kim, Sang‐Min Lee, Sungpyo Baek, Saeroonter Oh, Yoonmyung Lee, Sungjoo Lee   +6 more
wiley   +1 more source

Reinforcement-test-blank acquisition programming under the unmixed-list design in paired-associate learning [PDF]

, 1970
Chizuko Izawa
openalex   +1 more source

Gaussian‐Sigmoid Reinforcement Transistors: Resolving Exploration‐Exploitation Trade‐Off Through Gate Voltage‐Controlled Activation Functions

Advanced Functional Materials, EarlyView.
The characteristics of a vertical n–p–i–p heterostructure transistor device, which exhibits a voltage‐tunable transition between Gaussian and sigmoid functions, are investigated. The mixed state of the transfer curve enables the utilization of both exploitation and exploration, improving computational performance in reinforcement learning tasks ...
Jisoo Park, Juhyung Seo, Ryun‐Han Koo, Dinithi Jayasuriya, Nethmi Jayasinghe, Wonjun Shin, Amit R. Trivedi, Hocheon Yoo   +7 more
wiley   +1 more source

The intercalated reinforcement technique: Learning without differential total reinforcement between groups [PDF]

, 1973
Philip J. Bushnell, Kenneth R. Henry, Robert E. Bowman   +2 more
openalex   +1 more source

SMaRT Stacking: A Methodology to Produce Optimally Layered EMI Shields with Maximal Green Index Using Fused Deposition Modeling

Advanced Functional Materials, EarlyView.
Electromagnetic interference (EMI) shields consisting of polylactic acid (PLA) in layers with different concentrations of multiwalled carbon nanotubes (MWCNT) are produced using additive manufacturing. The permittivity function of layers with different filler concentrations is learned using data of homogeneous and randomly ordered shields.
Stijn De Smedt, Brecht Evens, Pramod Ravichandran, Panagiotis Patrinos, Frederik Van Loock, Ruth Cardinaels   +5 more
wiley   +1 more source