Results 211 to 220 of about 2,065,553 (347)
The Return of Pseudosciences in Artificial Intelligence: Have Machine Learning and Deep Learning Forgotten Lessons from Statistics and History? [PDF]
Jérémie Sublime
openalex +1 more source
A soft poly (3,4‐ethylenedioxythiophene):poly (styrenesulfonate)‐based electrode enables continuous, high‐quality recording of peripheral nerve activity. A neural network model integrating handcrafted and convolutional neural network‐based features decodes whisker movements with strong generalization, offering insights into peripheral nerve function ...
Liangpeng Chen+22 more
wiley +1 more source
Predicting clinical trial duration via statistical and machine learning models. [PDF]
Cho J, Xu Q, Wong CH, Lo AW.
europepmc +1 more source
This review explores the cutting‐edge development of bio‐integrated flexible electronics for real‐time hemodynamic monitoring in cardiovascular healthcare. It covers key physiological indicators, innovative sensing mechanisms, and materials considerations. This paper highlights the application of both invasive and non‐invasive devices in cardiovascular
Ke Huang, Zhiqiang Ma, Bee Luan Khoo
wiley +1 more source
Enhancing ERα-targeted compound efficacy in breast cancer threapy with ExplainableAI and GeneticAlgorithm. [PDF]
Pun Z, Xue Q, Zhang Y.
europepmc +1 more source
Large-Scale Machine Learning with Stochastic Gradient Descent
L. Bottou
semanticscholar +1 more source
This research presents a novel optimization method for the inverse design of flexible mechanical metamaterials, enhancing traditional strategies by evaluating deformation in subregions. Combining simulated annealing with a genetic algorithm, it improves design efficiency and enables customizable deformation paths.
Xueqing Cao+4 more
wiley +1 more source
Automatic diagnosis of extraocular muscle palsy based on machine learning and diplopia images. [PDF]
Jin XL, Li XM, Liu TJ, Zhou LY.
europepmc +1 more source
Unveiling Multi‐Scale Architectural Features in Single‐Cell Hi‐C Data Using scCAFE
scCAFE is a deep learning framework designed to identify multi‐scale 3D genome architectural features from single‐cell Hi‐C data without dense imputation. It predicts chromatin loops, TAD‐like domains, and A/B compartments, enabling efficient characterization of organization at the single‐cell level. scCAFE also identifies marker loop anchors, offering
Fuzhou Wang+12 more
wiley +1 more source
Machine learning model optimization for compressional sonic log prediction using well logs in Shahd SE field, Western Desert, Egypt. [PDF]
Saleh K, Mabrouk WM, Metwally A.
europepmc +1 more source