Results 61 to 70 of about 114,557 (285)

Neural Architecture Search Using Covariance Matrix Adaptation Evolution Strategy

Evolutionary Computation
Abstract Evolution-based neural architecture search methods have shown promising results, but they require high computational resources because these methods involve training each candidate architecture from scratch and then evaluating its fitness, which results in long search time. Covariance Matrix Adaptation Evolution Strategy (CMA-ES)
Sinha, Nilotpal, Chen, Kuan-Wen
openaire   +3 more sources

Continual Learning for Multimodal Data Fusion of a Soft Gripper

Advanced Robotics Research, EarlyView.
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley   +1 more source

Empirical Evaluation of Contextual Policy Search with a Comparison-based Surrogate Model and Active Covariance Matrix Adaptation

, 2019
Contextual policy search (CPS) is a class of multi-task reinforcement learning algorithms that is particularly useful for robotic applications. A recent state-of-the-art method is Contextual Covariance Matrix Adaptation Evolution Strategies (C-CMA-ES ...
Fabisch, Alexander
core   +1 more source

Machine‐Learning Decomposition Identifies a Big Two Structure in Human Personality with Distinct Neurocognitive Profiles

Advanced Science, EarlyView.
Using machine learning on a mega‐scale global dataset (n = 1,336,840) reveals a robust personality trait architecture beyond the Big Five. A Big Two model, broadly capturing social engagement and internal mentation, defines a geometric space that links personality to neurocognitive profiles.
Kaixiang Zhuang, Ji Chen, Jinfeng Han, Wei Cheng, Jiang Qiu, Jianfeng Feng, Simon Eickhoff, Deniz Vatansever   +7 more
wiley   +1 more source

Multi-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy

Sensors, 2023
In advanced transportation-management systems, variable speed limits are a crucial application. Deep reinforcement learning methods have been shown to have superior performance in many applications, as they are an effective approach to learning ...
Jianshuai Feng, Tianyu Shi, Yuankai Wu, Xiang Xie, Hongwen He, Huachun Tan   +5 more
doaj   +1 more source

MontePython 3: boosted MCMC sampler and other features

, 2018
MontePython is a parameter inference package for cosmology. We present the latest development of the code over the past couple of years. We explain, in particular, two new ingredients both contributing to improve the performance of Metropolis-Hastings ...
Brinckmann, Thejs, Lesgourgues, Julien
core   +1 more source

Consensus Formation and Change are Enhanced by Neutrality

Advanced Science, EarlyView.
Neutral agents are shown to enhance both the formation and overturning of consensus in collective decision‐making. A general mathematical model and experiments with locusts and humans reveal that neutrality enables robust consensus via simple interactions and accelerates consensus change by reducing effective population size.
Andrei Sontag, Janina A. Hoffmann, Tim Rogers, Christian A. Yates   +3 more
wiley   +1 more source

Linearizing and Forecasting: A Reservoir Computing Route to Digital Twins of the Brain

Advanced Science, EarlyView.
A new approach uses simple neural networks to create digital twins of brain activity, capturing how different patterns unfold over time. The method generates and recovers key dynamics even from noisy data. When applied to fMRI, it predicts brain signals and reveals distinctive activity patterns across regions and individuals, opening possibilities for ...
Gabriele Di Antonio, Tommaso Gili, Andrea Gabrielli, Maurizio Mattia   +3 more
wiley   +1 more source

Discovery of an Adaptive Neuroimmune Response Driving Itch and Fast Tick Removal with Implications for Preventing Pathogen Transmission

Advanced Science, EarlyView.
Itch‐induced tick removal (IITR): An acquired neuroimmune mechanism, itch‐induced tick removal, develops after repeated tick exposure, mobilizing T cells and macrophages at the tick bite site to trigger a rapid scratching response that facilitates timely tick removal within a critical window that precedes the transmission of many tick‐borne pathogens ...
Johannes S. P. Doehl, Tiago D. Serafim, Serena Doh, Charles S. Grugan, Eva Iniguez, Luana Rogerio, Ronja Frigard, Ranadhir Dey, Pedro Cecilio, Xinglong Gu, Pang‐Yen Tseng, Aline da Silva Moreira, Mahnaz Minai, James Oristian, Hans Ackerman, Steven Brooks, Caroline Percopo, Siu‐Ping Ng, Derron A. Alves, Lucas Tirloni, Jennifer M. Anderson, Adriana Marques, Fabiano Oliveira, Shaden Kamhawi, Daniel E. Sonenshine, José M. C. Ribeiro, Mark Hoon, Jesus G. Valenzuela   +27 more
wiley   +1 more source

Speed Estimation of a Double-Star Permanent Magnet Synchronous Motor Using an Optimized Extended Kalman Filter

International Transactions on Electrical Energy Systems
A mathematical model of a double-star permanent magnet synchronous motor is proposed, coupled with an estimator for speed, position, and currents based on an extended Kalman filter. This filter is optimized using a novel methodology.
Badreddine Naas, Lazhari Nezli, Mohamed Elbar, Ievgen Zaitsev   +3 more
doaj   +1 more source