AIMC Topic:
Learning

Clear Filters Showing 1191 to 1200 of 1372 articles

Replay as a Basis for Backpropagation Through Time in the Brain.

Neural computation
How episodic memories are formed in the brain is a continuing puzzle for the neuroscience community. The brain areas that are critical for episodic learning (e.g., the hippocampus) are characterized by recurrent connectivity and generate frequent off...

Generative artificial intelligence in secondary education: Applications and effects on students' innovation skills and digital literacy.

PloS one
As generative artificial intelligence (AI) rapidly transforms educational landscapes, understanding its impact on students' core competencies has become increasingly critical for educators and policymakers. Despite growing integration of AI technolog...

Relating Human Error-Based Learning to Modern Deep RL Algorithms.

Neural computation
In human error-based learning, the size and direction of a scalar error (i.e., the "directed error") are used to update future actions. Modern deep reinforcement learning (RL) methods perform a similar operation but in terms of scalar rewards. Despit...

Toward biologically realistic models of the motor system.

Neuron
In this issue of Neuron, Chiappa et al. describe how neural networks can be trained to perform complex hand motor skills. A key to their approach is curriculum learning, breaking learning into stages, leading to good control.

Constructing knowledge: the role of AI in medical learning.

Journal of the American Medical Informatics Association : JAMIA
The integration of large language models (LLMs) like ChatGPT into medical education presents potential benefits and challenges. These technologies, aligned with constructivist learning theories, could potentially enhance critical thinking and problem...

Learning Fixed Points of Recurrent Neural Networks by Reparameterizing the Network Model.

Neural computation
In computational neuroscience, recurrent neural networks are widely used to model neural activity and learning. In many studies, fixed points of recurrent neural networks are used to model neural responses to static or slowly changing stimuli, such a...

Judging robot ability: How people form implicit and explicit impressions of robot competence.

Journal of experimental psychology. General
Robots' proliferation throughout society offers many opportunities and conveniences. However, our ability to effectively employ these machines relies heavily on our perceptions of their competence. In six studies (N = 2,660), participants played a co...

Meta predictive learning model of languages in neural circuits.

Physical review. E
Large language models based on self-attention mechanisms have achieved astonishing performances, not only in natural language itself, but also in a variety of tasks of different nature. However, regarding processing language, our human brain may not ...