Click on talk titles to view videos (when available).
Click on author names to see abstracts.
Abstract: I will describe some insights in Russell's early papers, which became essential to our understanding of (many aspects of) computational complexity.
Abstract: I discuss issues of inverting feasibly computable functions, optimal discovery algorithms, and the constant overheads in their performance.
Abstract: The Conscious Turing Machine (CTM) is a simple formal TCS model sufficiently powerful to explain, at a high level, many phenomena generally associated with consciousness. Explanations derived from the model draw confirmation from consistencies at a high level (well above the level of neurons) with the cognitive neuroscience literature.
The CTM provides a natural framework for Artificial General Intelligence (AGI).
Our talk will describe the CTM, give the rationale for several of its design choices, and give a taste for how the TCS perspective provides insight.
Abstract: TBA
Abstract: TBA
Abstract: In this talk, we will explore several problems related to card guessing. In particular, how much memory is required in order to: (i) guess cards as well as the best player, (ii) play the Mirror Game and (ii) to generate a hard to guess permutation.
Abstract: Russell's "five worlds" framed my research on computational learning theory, but were never mentioned explicitly in any of our joint papers. I will explain the "five worlds" perspective on learning, describe working with Russell, and give a brief status update regarding each world.