Introduction to AI, Machine Learning and Python basics

Explore how artificial intelligence encompasses machine learning and deep learning, compare neural networks and backpropagation, and learn when to use ML vs DL for data-driven predictions.

Explore the differences between supervised and unsupervised learning, showing labeled data for classification and regression and unlabeled data for clustering and dimensionality reduction with iris flowers and apartment pricing examples.

Master linear regression in Excel to predict apartment prices from area using the least squares method, deriving y = a x + b and evaluating fit with r-squared.

Discover how classification tasks assign objects to limited classes, from loan approvals to iris flowers, and explore methods like decision trees, logistic regression, random forest, svm, and k-nearest neighbors.

Explore how clustering, an unsupervised learning method, groups data by similarity, contrasts with classification, and enables applications in retail segmentation, social networks, photo organization, and biology.

learn ensemble methods, including random forests, by combining multiple models to improve prediction accuracy and cancel errors, inspired by the wisdom of the crowd.

Explore how ensembles use majority voting, simple averaging, and weighted averaging to produce better predictions; assess when majority voting succeeds or fails and how weights impact results.

Learn ensemble methods such as bagging, boosting, random forests, and stacking, built on bootstrap aggregation from multiple resampled datasets to improve accuracy and use adaptive boosting.

Explore how random forest ensembles build multiple decision trees from sub-samples and random feature subsets, aggregate results by majority voting or averaging, delivering high accuracy albeit as a black box.

Explore how Python dominates machine learning and data analysis, and learn to use the Anaconda distribution with popular libraries and the Jupyter notebook environment.

Learn basic Python commands, including variables, printing, comments, math operations, type checks, and dynamic typing, plus output formatting and version checks.

Explore how the if-else statement controls Python program flow using the modulo operator to test even numbers and conditional printing, including speed limit examples.

Explore how the while statement functions as a control flow operator to drive loops, print numbers, and update counters with break and input examples.

Learn to predict apartment prices in Python using simple linear regression on area data, train with least squares, visualize results, and export predictions from Excel files.

Train a linear regression model to predict gdp from oil prices, using an excel dataset, and extend to a two-variable model with year for improved accuracy.

Predict Titanic survival using a linear support vector machine in Python. Learn to prepare data with median imputation, gender encoding, and a train-test split to evaluate model accuracy.

Build a neural network to classify clothing images using a 28 by 28 grayscale dataset; train with backpropagation across 60,000 training and 10,000 test images in a three-layer model.

Learn to use neural networks to analyze text, including building a movie review sentiment model. Explore text classification and translation, and convert text to numbers via tokenization on Google Colab.

Build a neural network to classify IMDB movie reviews as positive or negative using a ten-thousand word one-hot vector; train on twenty-five thousand reviews with binary cross-entropy, achieving 85% accuracy.