AIMC Topic: Problem Solving

Clear Filters Showing 11 to 20 of 146 articles

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

Neural networks : the official journal of the International Neural Network Society
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 for abstraction and reasoning.

Scientific reports
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...

Quo vadis, planning?

The Behavioral and brain sciences
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...

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

Nature chemical biology
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...

AI-induced hyper-learning in humans.

Current opinion in psychology
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. ...

Study of a PST-trained voice-enabled artificial intelligence counselor for adults with emotional distress (SPEAC-2): Design and methods.

Contemporary clinical trials
BACKGROUND: Novel and scalable psychotherapies are urgently needed to address the depression and anxiety epidemic. Leveraging artificial intelligence (AI), a voice-based virtual coach named Lumen was developed to deliver problem solving treatment (PS...

A deep reinforcement learning algorithm framework for solving multi-objective traveling salesman problem based on feature transformation.

Neural networks : the official journal of the International Neural Network Society
As a special type of multi-objective combinatorial optimization problems (MOCOPs), the multi-objective traveling salesman problem (MOTSP) plays an important role in practical fields such as transportation and robot control. However, due to the comple...

Exploring the performance and explainability of fine-tuned BERT models for neuroradiology protocol assignment.

BMC medical informatics and decision making
BACKGROUND: Deep learning has demonstrated significant advancements across various domains. However, its implementation in specialized areas, such as medical settings, remains approached with caution. In these high-stake environments, understanding t...

Detection method of organic light-emitting diodes based on small sample deep learning.

PloS one
In order to solve the surface detection problems of low accuracy, low precision and inability to automate in the production process of late-model display panels, a little sample-based deep learning organic light-emitting diodes detection model SmartM...