AI Medical Compendium Topic

Explore the latest research on artificial intelligence and machine learning in medicine.

Generalization, Psychological

Showing 21 to 30 of 78 articles

Clear Filters

Deep learning assisted sparse array ultrasound imaging.

PloS one
This study aims to restore grating lobe artifacts and improve the image resolution of sparse array ultrasonography via a deep learning predictive model. A deep learning assisted sparse array was developed using only 64 or 16 channels out of the 128 c...

DeepMethylation: a deep learning based framework with GloVe and Transformer encoder for DNA methylation prediction.

PeerJ
DNA methylation is a crucial topic in bioinformatics research. Traditional wet experiments are usually time-consuming and expensive. In contrast, machine learning offers an efficient and novel approach. In this study, we propose DeepMethylation, a no...

Stability analysis of stochastic gradient descent for homogeneous neural networks and linear classifiers.

Neural networks : the official journal of the International Neural Network Society
We prove new generalization bounds for stochastic gradient descent when training classifiers with invariances. Our analysis is based on the stability framework and covers both the convex case of linear classifiers and the non-convex case of homogeneo...

Strengthening transferability of adversarial examples by adaptive inertia and amplitude spectrum dropout.

Neural networks : the official journal of the International Neural Network Society
Deep neural networks are sensitive to adversarial examples and would produce wrong results with high confidence. However, most existing attack methods exhibit weak transferability, especially for adversarially trained models and defense models. In th...

A continuation method for image registration based on dynamic adaptive kernel.

Neural networks : the official journal of the International Neural Network Society
Image registration is a fundamental problem in computer vision and robotics. Recently, learning-based image registration methods have made great progress. However, these methods are sensitive to abnormal transformation and have insufficient robustnes...

A biologically inspired architecture with switching units can learn to generalize across backgrounds.

Neural networks : the official journal of the International Neural Network Society
Humans and other animals navigate different environments effortlessly, their brains rapidly and accurately generalizing across contexts. Despite recent progress in deep learning, this flexibility remains a challenge for many artificial systems. Here,...

Walking and falling: Using robot simulations to model the role of errors in infant walking.

Developmental science
What is the optimal penalty for errors in infant skill learning? Behavioral analyses indicate that errors are frequent but trivial as infants acquire foundational skills. In learning to walk, for example, falling is commonplace but appears to incur o...

Feature-wise scaling and shifting: Improving the generalization capability of neural networks through capturing independent information of features.

Neural networks : the official journal of the International Neural Network Society
From the perspective of input features, information can be divided into independent information and correlation information. Current neural networks mainly concentrate on the capturing of correlation information through connection weight parameters s...

A synergistic future for AI and ecology.

Proceedings of the National Academy of Sciences of the United States of America
Research in both ecology and AI strives for predictive understanding of complex systems, where nonlinearities arise from multidimensional interactions and feedbacks across multiple scales. After a century of independent, asynchronous advances in comp...

Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approach.

Neural networks : the official journal of the International Neural Network Society
The 6-Degree-of-Freedom (6-DoF) robotic grasping is a fundamental task in robot manipulation, aimed at detecting graspable points and corresponding parameters in a 3D space, i.e affordance learning, and then a robot executes grasp actions with the de...