By the course's end, students will:
-
be introduced to the many active areas of research in artificial intelligence, including: search, probabilistic & causal reasoning, data science, and machine learning.
-
understand existing approaches to a variety of classic and realistic AI problems, including: search, constraint satisfaction, inference, planning, probabilistic reasoning, classification, reinforcement learning, and deep learning.
-
gain practice using popular data-structures in AI, including: search trees, planning graphs, Bayesian Networks, Naive Bayes Classifiers, decision trees, and artificial neural networks.
-
become familiar with popular AI frameworks and libraries in Python, like Malmo and Scikit, and design artificial agents whose behaviors can be tangibly observed.
-
grasp the ongoing avenues for research in the field, investigating some efforts that suit their specific interests.
Visit the class Website to learn more.