Open-Ended Learning
Jonas discusses the potential of intelligent systems to learn continuously from their environment, emphasizing the need for machines to develop the right abstractions for effective decision-making. He highlights the limitations of current implementations and the exciting possibilities of creating open-ended systems that adapt and improve over time. Tim raises philosophical questions about knowledge primitives and the necessity of a framework for handling novelty, further enriching the conversation on the future of machine learning.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Jonas Hübotter (ETH) - Test Time Inference
Related Questions