אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

The emergence of very effective deep learning techniques in recent years has affected almost all areas of research remotely related to AI, and computer vision in particular has been changed irreversibly. In this talk I will focus on visual object recognitions. The incredible recent progress in this area, and the availability of very effective public domain tools for object recognition in images, allows us to reopen old questions and approach them from new directions with new tools. I will talk about two such questions. Specifically, in the first part of the lecture I will talk about curriculum learning, where a learner is exposed to examples whose difficulty level is gradually increased. This heuristic has been empirically shown to improve the outcome of learning in various models. Our main contribution is a theoretical result, showing that learning with a curriculum speeds up the rate of learning in the context of the regression and the hinge loss. Interestingly, we also show how curriculum learning and hard-sample mining, although conflicting at first sight, can coexist harmoniously within the same theoretical model. In the second part of the lecture I will talk about a new generative deep learning model, which we call GM-GAN. I will show how this model can be used for novelty detection, and also augment data in a semi-supervised setting when the labeled sample is small. I will conclude by showing how GM-GAN can be used for unsupervised clustering. Short Bio: Daphna Weinshall received the BSc degree in mathematics and computer science from Tel-Aviv University, Tel-Aviv Israel, in 1982. She received the MSc and PhD degrees in mathematics and statistics from Tel-Aviv University in 1985 and 1986, respectively, working on models of evolution and population genetics. Between 1987 and 1992, she visited the center for biological information processing at MIT and the IBM T.J. Watson Research Center. In 1993, she joined the Institute of Computer Science at the Hebrew University of Jerusalem, where she is now a full professor. Her research interests include computer and biological vision, as well as machine and human learning. Her recent interests include the learning of distance functions, object class recognition, cognitive passwords, and Virtual Reality in schizophrenia research.