Results 51 to 60 of about 8,974 (165)

Meta Reinforcement Learning for Automated Cyber Defence

Applied AI Letters, Volume 7, Issue 1, February 2026.
ABSTRACT Reinforcement learning (RL) solutions have shown considerable promise for automating the defense of networks to cyber attacks. However, a limitation to their real world deployment is the sample efficiency and generalizability of RL agents. This means that even small changes to attack types require a new agent to be trained from scratch.
Andrew Thomas, Nick Tillyer
wiley   +1 more source

Deep deterministic policy gradient - model-agnostic meta-learning framework: Efficient adaptation in continuous control tasks

Results in Engineering
Deep reinforcement learning (DRL) demonstrates superior performance in continuous control tasks. However, extensive training across a variety of environments is frequently necessitates extensive training.
Ebrahim Hamid Sumiea, Said Jadid Abdulkadir, Hitham Seddig Alhussian, Safwan Mahmood Al-Selwi, Alawi Alqushaibi, Mohammed Gamal Ragab, Abdul Muiz Fayyaz   +6 more
doaj   +1 more source

Task Transfer by Preference-Based Cost Learning

, 2019
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant ...
Huang, Wenbing, Jing, Mingxuan, Liu, Huaping, Ma, Xiaojian, Sun, Fuchun   +4 more
core   +1 more source

Nitrate Enhances Gastric Mucosa Defense and Repair Process in Ethanol‐Induced Gastric Ulcer Rats via the Notch–Tff2 Pathway

MedComm, Volume 7, Issue 2, February 2026.
Nitrate protects the three major barriers of the gastric mucosa, alleviating bleeding and inflammation of ethanol‐induced gastric ulcer in rats, and promotes migration of gastric epithelial cells, accelerating the restoration of the ulcerated epithelium, which is strongly related to TFF2, a gastric mucosal protective factor negatively regulated by the ...
Ying Liu, Xin Wen, Yuxuan Lin, Chunmei Zhang, Jinsong Wang, Guangyong Sun, Dong Zhang, Renhong Yan, Mo Chen, Songlin Wang, Shaorong Li   +10 more
wiley   +1 more source

Small Sample-Oriented Prediction Method of Mechanical Properties for Hot Rolled Strip Steel Based on Model Independent Element Learning

IEEE Access
In this paper, a new method based on Model-Agnostic Meta-Learning (MAML) is proposed to address the small sample problem in predicting the mechanical properties of hot rolled strip steel.
Hongyi Wu, Borui Zhang, Zhiwei Li
doaj   +1 more source

Machine Learning for Accelerating Energy Materials Discovery: Bridging Quantum Accuracy with Computational Efficiency

Advanced Energy Materials, Volume 16, Issue 2, 14 January 2026.
This perspective highlights how machine learning accelerates sustainable energy materials discovery by integrating quantum‐accurate interatomic potentials with property prediction frameworks. The evolution from statistical methods to physics‐informed neural networks is examined, showcasing applications across batteries, catalysts, and photovoltaics ...
Kwang S. Kim
wiley   +1 more source

Hypernetwork Approach to Bayesian MAML (Student Abstract)

Proceedings of the AAAI Conference on Artificial Intelligence
The main goal of Few-Shot learning algorithms is to enable learning from small amounts of data. One of the most popular and elegant Few-Shot learning approaches is Model-Agnostic Meta-Learning (MAML). In this paper, we propose a novel framework for Bayesian MAML called BH-MAML, which employs Hypernetworks for weight updates.
Borycki, Piotr, Kubacki, Piotr, Przewięźlikowski, Marcin, Kuśmierczyk, Tomasz, Tabor, Jacek, Spurek, Przemysław   +5 more
openaire   +2 more sources

Natural Products Targeting Notch Signaling in Cancer: Mechanistic Insights and Food‐Based Chemoprevention Potential

Food Frontiers, Volume 7, Issue 1, January 2026.
The Notch signaling pathway plays a dual role in cancer, acting as both a tumor promoter and suppressor depending on cellular context. This review highlights how natural products modulate Notch signaling to inhibit tumor initiation, progression, angiogenesis, and cancer stem cell maintenance.
Rabab Fatima, Parteek Prasher, Mousmee Sharma, Dietrich Büsselberg, Gabriela Figueroa‐González, Octavio Daniel Reyes‐Hernández, Edgar Yebrán Villegas‐Vázquez, Hernán Cortés, Gerardo Leyva‐Gómez, Jesús Herrera‐Bravo, Solomon Habtemariam, Javad Sharifi‐Rad, Monica Butnariu, Cristian Berar, Angela Caunii, William C. Cho   +15 more
wiley   +1 more source

High-Resolution PM₁₀ Estimation Using Satellite Data and Model-Agnostic Meta-Learning

Remote Sensing
Characterizing the spatial distribution of particles smaller than 10 μm (PM10) is of great importance for air quality management yet is very challenging because of the sparseness of air quality monitoring stations.
Yue Yang, Jan Cermak, Xu Chen, Yunping Chen, Xi Hou   +4 more
doaj   +1 more source

Mechanical Evaluation of Posterior Wall Acetabular Facture Fixation: Patient‐Specific Implants Versus Conventional Implants

Journal of Orthopaedic Research, Volume 44, Issue 1, January 2026.
ABSTRACT The aim of the study was to design a standardized mechanical test setup and a corresponding finite element analysis to assess the stability and strength of both patient‐specific and conventional implants for posterior wall acetabular fractures.
Miriam G. E. Oldhoff, Anne M. L. Meesters, Joep Kraeima, Mehool R. Acharya, Kaj ten Duis, Jean‐Paul P. M. de Vries, Bram B. J. Merema, Frank F. A. IJpma   +7 more
wiley   +1 more source