AIMC Topic: Problem Solving

Clear Filters Showing 1 to 10 of 139 articles

Mastering diverse control tasks through world models.

Nature Apr 2, 2025
Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement-learning algorithms can be readily applied to tasks similar to w...
Artificial Intelligence Algorithms Humans Problem Solving Reinforcement, Psychology Learning Task Performance and Analysis
View on PubMed DOI

Artificial intelligence learns to reason.

Science (New York, N.Y.) Mar 20, 2025
Julia has two sisters and one brother. How many sisters does her brother Martin have? Solving this tiny puzzle requires a bit of thinking. You might mentally picture the family of three girls and one boy and then realize that the boy has three sister...
Female Problem Solving Male Intelligence Artificial Intelligence Humans Thinking Language
View on PubMed DOI

Similar failures of consideration arise in human and machine planning.

Cognition Mar 13, 2025
Humans are remarkably efficient at decision making, even in "open-ended" problems where the set of possible actions is too large for exhaustive evaluation. Our success relies, in part, on processes for calling to mind the right candidate actions. Whe...
Problem Solving Humans Machine Learning Adult Decision Making
View on PubMed DOI

AI-powered standardised patients: evaluating ChatGPT-4o's impact on clinical case management in intern physicians.

BMC medical education Feb 20, 2025
BACKGROUND: Artificial Intelligence is currently being applied in healthcare for diagnosis, decision-making and education. ChatGPT-4o, with its advanced language and problem-solving capabilities, offers an innovative alternative as a virtual standard...
Female Adult Humans Artificial Intelligence Generative Artificial Intelligence Problem Solving Male Clinical Competence Patient Simulation Case Management Internship and Residency Clinical Reasoning
View on PubMed DOI

Synergistic learning with multi-task DeepONet for efficient PDE problem solving.

Neural networks : the official journal of the International Neural Network Society Jan 3, 2025
Multi-task learning (MTL) is an inductive transfer mechanism designed to leverage useful information from multiple tasks to improve generalization performance compared to single-task learning. It has been extensively explored in traditional machine l...
Neural Networks, Computer Machine Learning Learning Problem Solving Humans
View on PubMed DOI

Neural networks for abstraction and reasoning.

Scientific reports Nov 13, 2024
For half a century, artificial intelligence research has attempted to reproduce the human qualities of abstraction and reasoning - creating computer systems that can learn new concepts from a minimal set of examples, in settings where humans find thi...
Problem Solving Machine Learning Algorithms Humans Neural Networks, Computer Artificial Intelligence
View on PubMed DOI

Quo vadis, planning?

The Behavioral and brain sciences Sep 23, 2024
Deep meta-learning is the driving force behind advances in contemporary AI research, and a promising theory of flexible cognition in natural intelligence. We agree with Binz et al. that many supposedly "model-based" behaviours may be better explained...
Problem Solving Cognition Goals Artificial Intelligence Learning Humans
View on PubMed DOI

Multicellular artificial neural network-type architectures demonstrate computational problem solving.

Nature chemical biology Sep 16, 2024
Here, we report a modular multicellular system created by mixing and matching discrete engineered bacterial cells. This system can be designed to solve multiple computational decision problems. The modular system is based on a set of engineered bacte...
Escherichia coli Synthetic Biology Problem Solving Neural Networks, Computer
View on PubMed DOI

AI-induced hyper-learning in humans.

Current opinion in psychology Sep 11, 2024
Humans evolved to learn from one another. Today, however, learning opportunities often emerge from interactions with AI systems. Here, we argue that learning from AI systems resembles learning from other humans, but may be faster and more efficient. ...
Artificial Intelligence Learning Humans Problem Solving
View on PubMed DOI

AI-assisted learning for systems thinking in resolving ill-structured problems among healthcare students.

Medical education Sep 1, 2024
Humans Thinking Systems Analysis Problem Solving Artificial Intelligence Students, Medical
View on PubMed DOI
Popular Topics
Recent Journals