Qiang Liu, Department of Computer Science
University of Texas at Austin
As a fundamental technique for approximating and bounding distances between probability measures, Stein’s method has caught the attention in the machine learning community recently; some of the key ideas in Stein’s method have been leveraged and extended for developing practical and efficient computational methods for learning and using large scale, intractable probabilistic models.
Kristian Kersting
Computer Science Department
Centre for Cognitive Science
Technische Universität Darmstadt
Our minds make inferences that appear to go far beyond standard machine learning. Whereas people can learn richer representations and use them for a wider range of learning tasks, machine learning algorithms have been mainly employed in a stand-alone context, constructing a single function from a table of training examples.
Ivan Stelmakh, PhD candidate
Machine Learning Department, School of Computer Science
Carnegie Mellon University
Peer review is the backbone of scholarly research and fairness of this process is crucial for the successful development of academia. In this talk, we will discuss our two recent works on fairness of peer review. In the first part of the talk, we will focus on the automated assignment of papers to reviewers in the conference setup. We will show that the assignment procedure currently employed by NeurIPS and ICML does not guarantee fairness and may discriminate against some submissions. In contrast, we will present the assignment algorithm that simultaneously ensures fairness and accuracy of the resulting allocation.
Edith Elkind, Department of Computer Science
University of Oxford
Suppose that a group of agents want to select k > 1 alternatives from a given set, and each agent indicates which of the alternatives are acceptable to her: the alternatives could be conference submissions, applicants for a scholarship or locations for a fast food chain. In this setting it is natural to require that the set of winners represents the voters fairly, in the sense that large groups of voters with similar preferences have at least some of their approved alternatives in the winning set.
Chris Eliasmith, Director of the Centre for Theoretical Neuroscience
Department of Systems Design Engineering
Spiking neural networks (SNNs) have received little attention from the AI community, although they compute in a fundamentally different — and more biologically inspired — manner than standard artificial neural networks (ANNs). This can be partially explained by the lack of hardware that natively supports SNNs. However, several groups have recently released neuromorphic hardware that supports SNNs.
Han Zhao, PhD candidate
Carnegie Mellon University
Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis. While most previous works aim to diversify the representations, we explore the complementary direction by performing an adaptive and data-dependent regularization motivated by the empirical Bayes method.
Maxwell Ramstead, McGill University
The active inference framework explains a deeply puzzling characteristic of living systems, that they resist the natural tendency towards dissipation; namely, the entropic decay that is dictated by the second law of thermodynamics. Living systems manage to maintain themselves in a limited number of states, i.e., their phenotypical states. How do organisms accomplish this incredible feat? What does it mean to be alive? How are they integrated across the scales at which they exist — from subcellular processes and neural networks, to embodied action and culture? In the active inference framework, the actions and bodies of organisms encode expectations (or Bayesian beliefs) about the world, and act to make those expectations come true.
Mohammed Alliheedi, PhD candidate
David R. Cheriton School of Computer Science
Ontologies must provide the entities, concepts, and relations required by the domain being represented. The domain of interest in this paper is the biochemistry experimental procedure. The ontology language being used is OWL-DL. OWL-DL was adopted due to its well-balanced flexibility among expressiveness (e.g., class description, cardinality restriction, etc.), completeness, and decidability. These procedures are composed of procedure steps, which can be represented as sequences. Sequences are composed of totally ordered, partially ordered, and alternative subsequences.
Paulo Pacheco, PhD candidate
David R. Cheriton School of Computer Science
In this seminar I will discuss some of the current state-of-the-art methods for generating attention maps in weakly supervised (image level annotations) for classification tasks, aiming image segmentation inference and object localization.
Guojun Zhang, PhD candidate
David R. Cheriton School of Computer Science
The expectation-maximization (EM) algorithm has been widely used in minimizing the negative log likelihood (also known as cross entropy) of mixture models. However, little is understood about the goodness of the fixed points it converges to.