applied ai notes
i used to teach applied ai to undergrad students a while ago and, being a sucker for well-documented resources, i compiled all my notes, presentations, and code for them. i dont teach them anymore but i feel this might still be useful to someone. this course was inspired by CS50's AI (credit where it's due!), but includes some modifications and my own presentations filled with fun and silly analogies.
click on the title to access the compiled notion page or just use the list of resources below to go to specific topics.
github repo
complete collection of code examples, notebooks, and implementations
topic 1: object oriented programming
fundamentals of object oriented programming, python, and data structures
topic 2: search
search algo basics, dfs, bfs, gbfs, a* search, adversarial search, minimax, alpa-beta pruning
topic 3: knowledge
propositional logic, logical connections, entailment, inference, model checking
topic 4: uncertainty
probability, conditional probability, bayes' rule, joint probability, bayesian networks, sampling, markov models, hidden markov models
topic 5: optimization
local search, hill climbing, simulated annealing, linear programming,
topic 6: machine learning
basics of ml, supervised learning, classification, knn, linear regression, perceptron learning rule, svms, decision trees, overfitting, under fitting, evaluation metrics, regularisation, cross validation, regression, maths behind linear regression, correlation vs causation, ols estimation, assumptions of linear regression, multivariable regression, stepwise regression and feature selection, bagging and boosting algorithms, random forrest, xgboost, dimensionality reduction with pca, gradio, reinforcement learning (intro), k-means clustering
topic 7: neural networks
artificial neural networks. activation functions. gradient descent. backpropagation. overfitting.