Introduction to Artificial Intelligence (AI)

By the conclusion of the Introduction to Artificial Intelligence (AI) course, students will acquire a comprehensive understanding of AI fundamentals, including its definition and various subfields such as Machine Learning (ML), Deep Learning, Natural Language Processing (NLP), Robotics, and Expert Systems. They will gain insights into the historical development of AI and its contemporary applications, while also engaging in discussions about ethical implications and societal effects, including issues related to privacy, bias, and employment. Students will explore problem-solving strategies utilized in AI, learning about search algorithms like Breadth-First Search (BFS) and Depth-First Search (DFS), as well as heuristic techniques such as A* and greedy algorithms, applying these methods to basic challenges in puzzle-solving, pathfinding, and gaming scenarios.

Furthermore, students will delve into the basics of machine learning, distinguishing between its various types—supervised, unsupervised, and reinforcement learning—and familiarizing themselves with essential algorithms like linear regression, decision trees, and k-nearest neighbors (KNN). They will also learn to assess and validate machine learning models through metrics such as accuracy, precision, recall, and F1-score. Intermediate knowledge will encompass neural networks and deep learning, where students will understand the structure and function of neural networks, including artificial neurons, layers, and activation functions, and apply deep learning techniques to tasks like image recognition and classification. In the realm of Natural Language Processing (NLP), they will grasp fundamental concepts such as tokenization, stemming, and lemmatization, and engage in text classification, sentiment analysis, and named entity recognition (NER) using libraries like NLTK or spaCy. Lastly, students will explore reinforcement learning, focusing on how agents learn through interactions with their environment.