NYU Artificial Intelligence - Introduction to Machine Learning Fundamentals

Explore fundamental artificial intelligence concepts through this comprehensive course covering probability theory, classification algorithms, and optimization techniques. Begin with discrete probability fundamentals and progress through Naïve Bayes classification, including parameter estimation and Laplace smoothing for handling sparse data. Master binary classifier evaluation metrics and implement both binary and multi-class perceptron algorithms. Delve into logistic regression for both binary and multi-class problems, understanding the mathematical foundations and practical applications. Conclude with optimization theory and gradient ascent methods essential for machine learning model training. Access supplementary materials and detailed course content through the provided course website at https://atcold.github.io/NYU-AISP24/ to enhance your understanding of these core AI methodologies.