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...
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. ...
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...
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...
Neural networks : the official journal of the International Neural Network Society
39793491
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...
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...
Neural networks : the official journal of the International Neural Network Society
40112637
Neural models produce promising results when solving Vehicle Routing Problems (VRPs), but may often fall short in generalization. Recent attempts to enhance model generalization often incur unnecessarily large training cost or cannot be directly appl...
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...
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...