Artificial Intelligence I
Learn the history and concepts of AI, including intelligent agents, problem representations, and search techniques, in this comprehensive course.
Modules/Weeks
Weekly Effort
Discipline
School
Format
Cost
Course Description
- Design and implement intelligent agents capable of solving a variety of AI problems in real-world applications such as self-driving cars, face recognition, and tumor detection.
- Gain a broad understanding of fundamental concepts in Artificial Intelligence through lecture videos and quizzes.
- Apply basic techniques for building intelligent computer systems to address real-world challenges like web search, industrial robots, and missile guidance.
- Develop practical problem-solving skills in AI for Master’s/graduate-level learners, offering valuable preparation for future studies and careers in the field.
Course Prerequisites
- Linear algebra (vectors, matrices, derivatives)
- Calculus
- Basic probability theory
- Python programming experience
What You Will Learn
By the end of this course, learners will be able to:
Demonstrate a broad understanding of the fundamental techniques utilized in building intelligent computer systems, encompassing state-space problem representations, intelligent agents, and uninformed and heuristic search.
Utilize essential machine learning techniques, including linear models, K nearest neighbors, perceptrons, neural networks, and naive Bayes, to address real-world AI problems effectively.
Apply acquired practical problem-solving skills to tackle challenges in game playing, adversarial search, and logical agents.
Establish a solid foundation for further studies in AI, having covered topics such as the history of AI and concepts related to overfitting in machine learning.
Course Outline
Module 1: Introduction to AI
Module 2: Intelligent Agents and Uninformed Search
Module 3: Heuristic Search
Module 4: Adversarial Search and Games
Module 5: Machine Learning 1
Module 6: Machine Learning 2
Instructors
Dr. Ansaf Salleb-Aouissi's recent interdisciplinary research interests involve using advanced machine learning methods and large amounts of data to study medical problems, specifically premature birth and infantile colic. Alongside her research, Salleb-Aouissi is dedicated to education and is committed to advancing research on online self-learning and creating advanced tools for auto-grading, self-testing, and providing support to students in computer science and mathematics. Salleb-Aouissi's research has been published in several high-quality peer-reviewed papers, including JMLR, TPAMI, ECML, PKDD, COLT, IJCAI, ECAI, and AISTAT. She joined the Department of Computer Science as a lecturer in discipline in July 2015 and holds a PhD in computer science from the University of Orleans, France, and received postdoctoral training at INRIA, Rennes (France). Salleb-Aouissi was appointed as an associate research scientist at the Columbia University’s Center for Computational Learning Systems in 2006, and she has also served as an adjunct professor with the Computer Science Department and the Data Science Institute in 2014 and 2015.
Please note that there are no instructors or course assistants actively monitoring this course.