Ashokkumar Patel, PhD

Machine learning methods and applications. The course focuses on models and algorithms that learn from data. It examines how machine learning pipelines are designed and implemented, including dataset exploration, data preparation, feature engineering, model selection, training, evaluation, tuning, and deployment. Key algorithms are presented, including decision trees, artificial neural networks, k-nearest neighbors, regression, and Bayesian methods. Both supervised and unsupervised learning techniques are examined through practical applications.

Advanced coverage of machine learning algorithms and applications to computer vision, data mining and social media. Specifically, the course focuses on data pre-processing, feature extraction, supervised/unsupervised learning, graphical model, deep learning, and other advanced machine learning topics. The course will also explore several real-world problems, e.g., visual detection/recognition, topics discovery, social media analytics using machine learning approaches.

Fundamental knowledge for capturing and analyzing large-scale data from diverse fields including human behavior, sensors, biological signals, and finance. The course introduces platforms for data storage systems and distributed processing of large datasets, covering big data pipeline concepts: collection, storage, ingestion, processing, analytics, and visualization. Students will work with platforms such as AWS Athena, AWS Glue, Kinesis, Elasticsearch, Kibana, Hadoop HDFS and MapReduce, and Spark.

The relational, hierarchical, and network approaches to database systems, including relational algebra and calculus, data dependencies, normal forms, data semantics, query optimization, and concurrency control on distributed database systems.