The free energy principle, and its corollary active inference, constitute a bio-inspired theory
that assumes biological agents act to remain in a restricted set of preferred states of the …

Active learning is a decision-making process. In both abstract and physical settings, active
learning demands both analysis and action. This is a review of active learning in robotics …

In this work, we aim to characterize the statistical complexity of realizable regression both in
the PAC learning setting and the online learning setting. Previous work had established the …

The book's core argument is that an artificial intelligence that could equal or exceed human
intelligence—sometimes called artificial general intelligence (AGI)—is for mathematical …

We develop an economic perspective on algorithmic fairness. Algorithmic bias and fairness
issues are appearing in an increasing variety of economic research literatures. Our …

In this paper, we offer an original framework to study Artificial Intelligence (AI). The
perspective we propose is based on the idea that AI is a system technology, and that a …

This position paper discusses the requirements and challenges for responsible AI with
respect to two interdependent objectives:(i) how to foster research and development efforts …

An impossibility theorem demonstrates that a particular problem or set of problems cannot
be solved as described in the claim. Such theorems put limits on what is possible to do …

Combinations of healthcare claims data with additional datasets provide large and rich
sources of information. The dimensionality and complexity of these combined datasets can …

We present a minimax optimal learner for the problem of learning predictors robust to
adversarial examples at test-time. Interestingly, we find that this requires new algorithmic …