The intersection of cognitive science, AI, and computational neuroscience is discussed. There is a bidirectional flow of ideas between these fields, AI has influenced neuroscience and vice versa. Questions whether imitating the brain is the best way to build AI, or if it is better to find engineering solutions, pointing out the successes and failures of both approaches. There is an importance of incorporating key cognitive ingredients, such as intuitive theories, compositionality, learning-to-learn, and causality, into AI systems to achieve more human-like intelligence. Current AI systems lack these ingredients, highlighting the need for AI researchers to consider higher-level cognitive principles. Cognitive plausibility is encouraged over strict biological accuracy in the pursuit of human-like AI.

Link to article: https://www.cambridge.org/core/journals/behavioral-and-brain-sciences/article/building-machines-that-learn-and-think-like-people/A9535B1D745A0377E16C590E14B94993

Hosted on Acast. See acast.com/privacy for more information.