First meeting of the semester. Introduction for new members, and planning for what people would like to see us do in the coming weeks and months.

Deep learning has enabled incredible advances in computer vision, natural language processing, and general pattern understanding. Success in this space spans many domains including object detection, speech recognition, natural language processing, and action/scene interpretation. For targeted tasks, results are on par with and often surpass the abilities of humans. This talk addresses two limitations of current deep learning research: 1) connecting multi-modal inputs such as vision and language into a common latent representation expose weaknesses in vector representation; and 2) creating CNNs for graphs is problematic as neither FIR filtering or common pooling techniques are applicable. This talk addresses these limitations and highlights recent discoveries and research done at RIT.

In this talk, I will provide a basic introduction to the Bayesian paradigm along with various examples illustrating its central role in statistical machine learning and data science. I will certainly highlight how the Bayesian school of thought gave rise to a multitude of fascinating and compelling scientific computing ideas and developments. I intend to make this talk informal and will eagerly welcome questions and remarks throughout my delivery of it.

This will be an overview of various techniques for evaluating derivatives numerically, as well as rules of thumb and general advice for when to use each method. Audience questions are encouraged.

The human being is comprised of two parts: rational and emotional side. The emotional state impacts not only reasoning and behaviour of person who is experiencing it but also other people surrounding him. In the seminar, computer modelling of human emotions, as well as human group emotions, will be discussed. Further, the listeners will be introduced to some exsting and currently in-progress applications of believable human simulation.