AI and Machine Learning

Sashikumaar G

Professor

Dept. Computational and Data Sciences, IISc

Objective

The objective of this course is to provide a comprehensive understanding of AI concepts, techniques, and practical applications using Python, enabling participants to develop and deploy AI solutions to real-world problems.

Syllabus

Introduction to AI and Python: Overview of AI, history, Python basics, essential libraries (NumPy, Pandas, Matplotlib). Data Preprocessing and Exploration: Data types, collection, preprocessing (missing data, normalization), Exploratory Data Analysis (EDA). Machine Learning Fundamentals: Key concepts, supervised vs. unsupervised learning, linear regression, model evaluation metrics. Classification Algorithms: Logistic regression, decision trees, evaluation metrics (accuracy, precision, recall, F1 score). Advanced Machine Learning Techniques: Support Vector Machines (SVM), ensemble methods (random forests, gradient boosting), hyperparameter tuning. Unsupervised Learning: Clustering (K-means, hierarchical), dimensionality reduction (PCA, t-SNE). Neural Networks and Deep Learning: Basics of neural networks, deep learning with TensorFlow/Keras. Natural Language Processing (NLP): Text preprocessing, sentiment analysis, word embeddings (Word2Vec, GloVe). Computer Vision: Image processing with OpenCV, Convolutional Neural Networks (CNNs). AI in Practice: Deploying models, Flask for deployment, AI applications, ethical considerations. Capstone Project involves project planning and proposal, selecting a problem statement, data collection and preparation, implementation of learned techniques, and model building and evaluation. Project Presentation and Course Wrap-Up includes project demonstrations, peer review, feedback, a course recap, Q&A, discussion on future directions in AI.

Target Audience

This course is designed for a diverse range of participants, including working professionals who are interested in enhancing their skills and knowledge in AI and Machine Learning.