Related papers: From Manifestations to Cognitive Architectures: a …
Many modern learning tasks require models that can take inputs of varying sizes. Consequently, dimension-independent architectures have been proposed for domains where the inputs are graphs, sets, and point clouds. Recent work on graph…
In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…
Abstraction is essential for reducing the complexity of systems across diverse fields, yet designing effective abstraction methodology for probabilistic models is inherently challenging due to stochastic behaviors and uncertainties. Current…
Computational metacognition represents a cognitive systems perspective on high-order reasoning in integrated artificial systems that seeks to leverage ideas from human metacognition and from metareasoning approaches in artificial…
This article provides an analytical framework for how to simulate human-like thought processes within a computer. It describes how attention and memory should be structured, updated, and utilized to search for associative additions to the…
Solutions relying on artificial intelligence are devised to predict data patterns and answer questions that are clearly defined, involve an enumerable set of solutions, clear rules, and inherently binary decision mechanisms. Yet, as they…
Mathematical models are increasingly used in both academia and the pharmaceutical industry to understand how phenotypes emerge from systems of molecular interactions. However, their current construction as monolithic sets of equations…
Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For example, Transformers segment by position, and object-centric architectures decompose images into…
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalization to data drawn from unseen but related distributions, a…
World models are emerging as a transformative paradigm in artificial intelligence, enabling agents to construct internal representations of their environments for predictive reasoning, planning, and decision-making. By learning latent…
As the discipline has evolved, research in machine learning has been focused more and more on creating more powerful neural networks, without regard for the interpretability of these networks. Such "black-box models" yield state-of-the-art…
The rise of Generative AI, and Large Language Models (LLMs) in particular, is fundamentally changing cognitive processes in knowledge work, raising critical questions about their impact on human reasoning and problem-solving capabilities.…
The research of artificial intelligence is undergoing a paradigm shift from prioritizing model innovations over benchmark scores towards emphasizing problem definition and rigorous real-world evaluation. As the field enters the "second…
The development of large language models (LLMs) is limited by a lack of explainability, the absence of a unifying theory, and prohibitive operational costs. We propose a neuro-theoretical framework for the emergence of intelligence in…
Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making. But with increased power and accuracy also comes higher complexity, making it hard for users to…
Knowledge is the most precious asset of humankind. People extract the experience from the data that provide for us the reality through the feelings. Generally speaking, it is possible to see the analogy of knowledge elaboration between…
We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore…
Utilising quantum computing technology to enhance artificial intelligence systems is expected to improve training and inference times, increase robustness against noise and adversarial attacks, and reduce the number of parameters without…
Sustainable AI is a subfield of AI for concerning developing and using AI systems in ways of aiming to reduce environmental impact and achieve sustainability. Sustainable AI is increasingly important given that training of and inference…
As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a…