Artificial Intelligence for Beginners: Understand the basics

Explore the relationship between artificial intelligence, machine learning, and deep learning, and learn the three main types of machine learning: supervised, unsupervised, and reinforcement.

Explore supervised and unsupervised machine learning, including how training and testing work with labeled data in supervised learning and how unsupervised learning discovers patterns without guidance.

Explore reinforcement machine learning, where a model observes the environment, takes actions, and learns from rewards and mistakes to improve performance and decision making.

Explore regression in machine learning, where models predict continuous outputs by finding patterns in data. See real-world examples like rainfall trends and COVID-19 case forecasting.

Learn classification machine learning, a supervised approach that uses labeled data to assign inputs to predefined classes. See fruit sorting, social media ads, Amazon reviews, and spam detection as examples.

Explore unsupervised learning by examining clustering, which groups similar data into clusters without labels. Apply clustering to social media to identify patterns, target audiences, and fraud signals.

Compare classification and clustering in machine learning with examples like apples vs bananas and unlabeled data. Explore how regression and clustering support self-driving cars in object detection and decision making.

Discover the three parts of artificial intelligence—dataset, learning algorithm, and prediction—and learn how inputs, steps, and outputs drive AI from data types like numerical, pictorial, and text datasets.

Learn to build an image-based object detection model that differentiates cats and dogs by training on labeled images in Teachable Machine, then save, export, and share the model.

Explore hands-on image recognition projects, train and explain your model with a dataset, and create video assignments showing object, vehicle, fruit, and plant identifiers for teacher submission.

Develop a mask detection model by collecting own images for two classes (mask and no mask), training, testing with varied angles, and saving the project to drive.

Understand how epochs, batches, batch size, batch number, and learning rate shape model training and accuracy for practical AI applications.

Develop an audio detection module by creating a three-class classifier for background noise, clap, and snap, recording samples, training the model, and validating its performance in Teachable Machines.

Explore the basics of computer programming and coding in this artificial intelligence for beginners course, focusing on how a computer follows a sequence of instructions using languages like Python.

Begin level two by learning Python basics and programming AI models, including regression, image classification, and neural networks. Explore hands-on projects like rock, paper, scissors to understand AI.