Symmetries play a central role in reducing the complexity of reinforcement learning problems, yet most existing approaches rely on fixed group actions or predefined state abstractions. Classical reinf...

That’s a good thing.

For some psychologists, it's becoming more common to use AI systems to replace human thinking in research. That's a very risky choice based on misconceptions, warn Iris van Rooij and Olivia Guest in a...

The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex s…

The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex s…

The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex scenarios. One way to address this issue has focuse...

Simulations are an indispensable step in the cycle of theory development and refinement, helping researchers formulate precise definitions, generate models, and make accurate predictions. This paper i...

Simulations are an indispensable step in the cycle of theory development and refinement, helping researchers formulate precise definitions, generate models, and make accurate predictions. This paper i...

We, the undersigned organisations and individuals, urge you in the strongest possible terms to reject the deletion of the Article 49(2) transparency safeguard for high-risk AI systems that is proposed...

The research presented in this paper advances the integration of Hebbian learning into Convolutional Neural Networks (CNNs) for image processing, syst…

Commission proposes pauses to provisions in digital rule book

YouTube video by librebel

Olivia Guest & Iris van Rooij urge teachers and scholars to reject tools that commodify learning, deskill students, and promote illiteracy.

Learning efficient representations allows robust processing of data, data that can then be generalised across different tasks and domains, and it is t…

Learning efficient representations allows robust processing of data, data that can then be generalised across different tasks and domains, and it is t…

In this paper, we propose a framework to extract the algebra of the transformations of worlds from the perspective of an agent. As a starting point, we use our framework to reproduce the symmetry-base...

In this paper, we propose a framework to extract the algebra of the transformations of worlds from the perspective of an agent. As a starting point, we use our framework to reproduce the symmetry-base...

YouTube video by CSER Cambridge

YouTube video by Future of Intelligence

The University of Sussex mourns the loss of Professor Margaret (Maggie) Boden, a pioneering figure in cognitive science and artificial intelligence.

A multidisciplinary conference on the future of comics, technology, and creativity

Website of the Artificial Reseach Centre, CitAI. Seminars.

The European Union is committed and determined to become a global leader in Artificial Intelligence, a leading AI continent.

The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex scenarios. One way to address this issue has focuse...

The UK Health Security Agency (UKHSA) is harnessing the power of artificial intelligence (AI) to address health security challenges. Here are 3 examples of projects that demonstrate how we're using cu...

Andrew Barto and Richard Sutton are the recipients of the 2024 ACM A.M. Turing Award for developing the conceptual and algorithmic foundations of reinforcement learning. In a series of papers beginning in the 1980s, Barto and Sutton introduced the main ideas, constructed the mathematical foundations, and developed important algorithms for reinforcement learning—one of the most important approaches for creating intelligent systems.

Having machines learn from experience was once considered a dead end. It’s now critical to artificial intelligence, and work in the field has won two men the highest honor in computer science.

Motivated by the recent putative reproducibility crisis, we discuss the relationship between the replicability of scientific studies, the reproducibility of results obtained in these replications, and...

The idea that human cognition is, or can be understood as, a form of computation is a useful conceptual tool for cognitive science. It was a foundational assumption during the birth of cognitive scien...

Volume 7, issue 4 articles listing for Computational Brain & Behavior

Website of the Artificial Reseach Centre, CitAI. Academic Jobs.