An ecological approach to Artificial Intelligence
In this blogpost we discuss how the field of Human Behavioral Ecology can guide our pursuit of Artificial Intelligence agents with human-like abilities. We first propose a conceptual framework aiming at facilitating inter-disciplinary discussions between research of natural and artificial intelligence and then delve into some of our computational studies.
Designing artificial conversational agents to train children's curiosity during learning, a proof of concept through the Kids Ask project
Kids Ask is a project that aims to design innovative educational technologies that can stimulate and support the epistemic curiosity of young learners and that leverage the social benefits of using artificial conversational agents.
Watching artificial intelligence through the lens of cognitive science methodologies
Utilizing a large size of language models contributes to recent advances in machine learning literature. However, interpreting what representations these models acquire is challenging due to their computational complexity. How can we understand the models functionally? This blog post suggests importing cognitive science methodologies to interpret their functional mechanisms. We introduce a way to conduct cognitive science experiments for machine learning models and analyze the models’ internal representation using cognitive neuroscience methodologies.
Guiding and Learning Without Common Ground: a New Interactive Learning Paradigm
Humans have an outstanding ability to teach and learn form each other without relying on pre-established communication protocol (not even expressing rewards). Could machine do the same? In this blog post we propose a new interactive learning paradigm to investigate this question.
Learning Sensorimotor Agency in Cellular Automata
In this blogpost, we explore the concepts of embodiment, individuality, self-maintenance and sensorimotor agency within a cellular automaton (CA) environment. Whereas those concepts are central in theoretical biology and cognitive science, it remains unclear how such behaviors can emerge in a CA-like environment made only of low-level particles and physical rules. We present a novel set of tools (based on curriculum learning, diversity search and gradient descent over a differentiable CA) to automatically learn the rules leading to the emergence of such behaviors. Our method is able to discover self-organizing agents with strong coherence and generalization to out-of-distribution changes, reminiscent of the remarkable robustness of living organisms to maintain specific functions despite environmental and body perturbations.
Intelligent behavior depends on the ecological niche: Scaling up AI to human-like intelligence in socio-cultural environments
In this blog post, Pierre-Yves Oudeyer discusses with Manfred Eppe to present his perspective on the future of AI and machines models of human-like intelligence. The discussion explains how developmental and evolutionary theories of human cognition should further inform artificial intelligence. This emphasizes the role of ecological niches in sculpting intelligent behavior, and in particular that human intelligence was fundamentally shaped to adapt to a constantly changing socio-cultural environment. A major limit of current work in AI is that it is missing this perspective, both theoretically and experimentally. One promising approach to address these limits is developmental artificial intelligence, modeling infant development through multi-scale interaction between intrinsically motivated learning, embodiment and a fastly changing socio-cultural environment.
Newer