Results 111 to 120 of about 93,556 (252)

Nonlinear Value Function Approximation Method With Easy Hyperparameter Tuning and Convergence Guarantee

IEEE Access
Reinforcement Learning is a branch of machine learning to learn control strategies that achieve a given objective through trial-and-error in the environment.
Yuuya Watabe, Takeshi Shibuya
doaj   +1 more source

Spectral Decomposition of Chemical Semantics for Activity Cliffs‐Aware Molecular Property Prediction

Advanced Science, EarlyView.
PrismNet mimics chemical intuition by functioning as a computational prism, refracting molecular graphs into complementary semantic views and spectral frequencies. This dual‐decomposition strategy effectively captures both global topologies and subtle “activity cliff” perturbations.
Chaoyang Xie, Junhu Xu, Guangyi Huang, Shihang Wang, Mutian He, Xinyu Dong, Huiyang Hong, Xiaojun Yao, Qi Wang, Yuquan Li   +9 more
wiley   +1 more source

Evaluating Coding Proficiency of Large Language Models: An Investigation Through Machine Learning Problems

IEEE Access
Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, but their effectiveness in coding workflows, particularly in machine learning (ML), requires deeper evaluation.
Eunbi Ko, Pilsung Kang
doaj   +1 more source

Data‐Driven Feedback Identifies Focused Ultrasound Exposure Regimens for Improved Nanotheranostic Targeting of the Brain

Advanced Science, EarlyView.
Machine learning models predict in real time the onset of harmful microbubble collapse during microbubble‐enhanced focused ultrasound (MB‐FUS) and enable dynamic adjustment of sonication to prevent cavitation‐induced damage. This predictive control expands the safe operating window for bloodbrain barrier opening, enhancing nanoparticle delivery and ...
Hohyun Lee, Victor Menezes, Shiqin Zeng, Chulyong Kim, Cynthia M. Baseman, Jae Hyun Kim, Samhita Padmanabhan, Pranav Premdas, Naima Djeddar, Anton Bryksin, Nikhil Pandey, Pavlos Anastasiadis, Anthony J. Kim, Tobey J. MacDonald, Chetan Bettegowda, Graeme F. Woodworth, Felix J. Herrmann, Costas Arvanitis   +17 more
wiley   +1 more source

Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction

Advanced Science, EarlyView.
Molecular foundation models can provide accurate predictions for a large set of downstream tasks. We develop MMELON, an approach that integrates pre‐trained graph, image, and text foundation models and validate our multi‐view model on over 120 tasks, including GPCR binding.
Parthasarathy Suryanarayanan, Yunguang Qiu, Shreyans Sethi, Diwakar Mahajan, Hongyang Li, Yuxin Yang, Elif Eyigoz, Aldo Guzmán‐Sáenz, Daniel E. Platt, Timothy H. Rumbell, Kenney Ng, Sanjoy Dey, Myson Burch, Bum Chul Kwon, Pablo Meyer, Feixiong Cheng, Jianying Hu, Joseph A. Morrone   +17 more
wiley   +1 more source

His‐MMDM: Multi‐Domain and Multi‐Omics Translation of Histopathological Images with Diffusion Models

Advanced Science, EarlyView.
His‐MMDM is a diffusion model‐based framework for scalable multi‐domain and multi‐omics translation of histopathological images, enabling tasks from virtual staining, cross‐tumor knowledge transfer, and omics‐guided image editing. ABSTRACT Generative AI (GenAI) has advanced computational pathology through various image translation models.
Zhongxiao Li, Tianqi Su, Bin Zhang, Wenkai Han, Sibin Zhang, Guiyin Sun, Yuwei Cong, Xin Chen, Jiping Qi, Yujie Wang, Shiguang Zhao, Hongxue Meng, Peng Liang, Xin Gao   +13 more
wiley   +1 more source

Using crafted features and polar bear optimization algorithm for short-term electric load forecast system

Energy and AI
Short-term load forecasting (STLF) can be utilized to predict usage fluctuation in a short time period and accurate forecasting can save a big chunk of a country's economic loss.
Mansi Bhatnagar, Gregor Rozinaj, Radoslav Vargic   +2 more
doaj   +1 more source

Generating Dynamic Structures Through Physics‐Based Sampling of Predicted Inter‐Residue Geometries

Advanced Science, EarlyView.
While static structure prediction has been revolutionized, modeling protein dynamics remains elusive. trRosettaX2‐Dynamics is presented to address this challenge. This framework leverages a Transformer‐based network to predict inter‐residue geometric constraints, guiding conformation generation via physics‐based iterative sampling. The resulting method
Chenxiao Xiang, Wenkai Wang, Zhenling Peng, Jianyi Yang   +3 more
wiley   +1 more source

Hybrid CNN-LSTM model with efficient hyperparameter tuning for prediction of Parkinson's disease. [PDF]

Sci Rep, 2023
Lilhore UK, Dalal S, Faujdar N, Margala M, Chakrabarti P, Chakrabarti T, Simaiya S, Kumar P, Thangaraju P, Velmurugan H.   +9 more
europepmc   +1 more source

Hyperparameter Tuning Through Pessimistic Bilevel Optimization

Automated hyperparameter search in machine learning, especially for deep learning models, is typically formulated as a bilevel optimization problem, with hyperparameter values determined by the upper level and the model learning achieved by the lower-level problem.
Ustun, Meltem Apaydin, Xu, Liang, Zeng, Bo, Qian, Xiaoning   +3 more
openaire   +2 more sources