Teaching

Deep Learning (40719)

The course helps to understand the fundamentals of Deep Learning. The course starts off gradually with multi-layer preceptrons and it progresses into the more complicated concepts such as attention and sequence-to-sequence models. This course also covers other models of deep learning such as convolutional neural networks, recurrent neural networks, deep generative models such as autoregressive, GAN, VAE, NFM, representation learning, and deep reinforcement learning methods. We use frameworks such as PyTorch and Tensorflow, which are very important for implementing deep Learning models.

Class Website

Machine Learning Theory (40718)

Machine learning theory concerns questions such as: What kinds of guarantees can we prove about practical machine learning methods, and can we design algorithms achieving desired guarantees? This course answers these questions by studying the theoretical aspects of machine learning, with a focus on statistically and computationally efficient learning. Broad topics will include: PAC-learning, uniform convergence, PAC-Bayesian, model selection; supervised learning algorithms including SVM, boosting, kernel methods; online learning algorithms, ranking algorithms, and analysis; unsupervised learning with guarantees.

Class Website

Machine Learning (40717)

This course will introduce the field of machine learning, in particular focusing on the core concepts of supervised, unsupervised learning, and reinforcement learning. In supervised learning we will discuss algorithms which are trained on input data labelled with a desired output and learn a function mapping from the input to the output. Unsupervised learning aims to discover latent structure in an input samples where output labels are not available. In reinforcement learning, we will discuss models and algorithms which are trained on input data when the evaluative feedback is available.

Class Website

Data Mining (40714)

This course discusses techniques for preprocessing data before mining and presents the concepts related to data warehousing, online analytical processing (OLAP), and data generalization. It presents methods for mining frequent patterns, sequence mining, graph mining, associations, and correlations. It also presents methods for dimensionality reduction, data classification and prediction, data-clustering approaches, and outlier analysis.

Class Website

Modern Information Retrieval (40324)

Information retrieval is the process through which a computer system can respond to a user's query for text-based information on a specific topic. Information retrieval was one of the first and remains one of the most important problems in the domain of natural language processing. Web search is the application of information retrieval techniques to the largest corpus of text anywhere and it is the area in which most people interact with information retrieval systems most frequently. In this course, we will cover basic and advanced techniques for building text-based information systems, including efficient text indexing, Boolean and vector-space retrieval models, evaluation and interface, issues, information retrieval techniques for the web, including crawling, link-based algorithms, and metadata usage, document clustering and classification, traditional and machine learning-based ranking approaches, questiona and answering systems, and recommender systems.

Class Website