Artificial Intelligence for Beginners: Python & AI Basics

Explore how programming turns human commands into computer actions using Python, a modern object oriented scripting language. Learn Python’s guiding philosophies—beautiful, explicit, and simple—to write readable code for ai projects.

Explore Python basics in Google Colab, write your first Hello World program with print and f-strings, and learn variables, data types, tuples, lists, and dictionaries.

Learn Python loops and conditional statements by building a while loop that repeats until the password matches, and a for loop that iterates over an animal sequence to print names.

Learn to define and call functions in Python, pass arguments, and understand the print versus return distinction through a prime numbers example.

Learn how Python classes define attributes and methods, create objects with a constructor, and use self to initialize robots and flowers through practical examples.

Learn how Python arrays store multiple values of the same type, compare them with lists, and perform length, indexing, slicing, and core array operations.

Learn to write robust python programs by using consistent indentation to define blocks and avoid errors, and understand that variables are created on assignment with hash comments.

Identify libraries as reusable code blocks you can import. Explore NumPy for arrays, OS for operating system interactions, Sklearn for machine learning, and Pandas for data analysis.

Learn to code ai models in python and apply linear regression, forming a best-fit line with slope and intercept from rainfall data with days as x and rainfall as y.

download the required data files from attachments, unzip on desktop, and upload the skillet courses folder to Google Drive so you can import and use those files in your program.

Build a five input multi dimensional regression model to predict final scores from study time, absences, failures, assignments, and midterm.

Define and train a linear regression model using sklearn, evaluate with a test set, and print predictions versus actual scores to demonstrate model performance.

Learn to build a handwritten digit classification model using the mnist 784 dataset and logistic regression in sklearn, working with 28 by 28 pixel images and 784 features.

Train a logistic regression model to classify handwritten digits using 28 by 28 images, tune tolerance and max iterations, and predict digits from test data.

Learn to build a content-based movie recommendation system using cosine similarity and the count vectorizer to suggest movies similar by keywords, cast, genre, and director.

Build a Netflix-like movie recommendation system by creating a count matrix from combined features with CountVectorizer, then sort similarities using a lambda-based key and cosine similarity.

Explore how the human nervous system uses neurons to sense and transmit signals, and translate these ideas into artificial neural networks with inputs, weights, and activation.

Explore how a neural network uses inputs, weights, and a hidden layer to compute the car price, illustrating how hidden neurons capture complex input combinations for precise outputs.

Explore how neural networks learn through training, from hard-coded rules to self-learning models, using backpropagation to minimize error.

Explore convolutional neural networks (CNNs) for image analysis, learning how layers, filters, and pooling detect edges, shapes, and objects, and build a rock, paper, scissors game using Python.

Learn to build a rock, paper, scissors CNN in Google Colab by capturing webcam images, augmenting data with image data generator, and training a TensorFlow Keras model with CNN layers.

Learn to code a CNN in Google Colab that recognizes rock, paper, scissors gestures by capturing labeled images with a webcam and preparing a training dataset.

Augment the rock, paper, and scissors dataset with image data generator and train a cnn to reach about 92% accuracy, saving the model as selfmade model.h5.

Leverage Google's pre-trained mobilenet v2 as a frozen base, add global average pooling and a three-class dense head to recognize rock, paper, or scissors, then integrate it into the game.