Introduction to AI, Machine Learning and Data Science

Artificial intelligence replicates human intelligence in machines programmed to think like humans, performing ordinary tasks and learning from past experiences and historical data through real-time examples.

Explore data science and machine learning as tools to extract actionable insights from data, build models, and classify, predict, or recommend outcomes for business decisions.

Discover how deep learning uses layered neural networks where neurons make decisions across inputs to produce outputs, shaped by architecture.

Explore how natural language processing uses AI and machine learning to analyze plain english text like product reviews and questions, converting it into numerical factors for sentiment analysis.

Explore computer vision by applying machine learning to data from what we see, such as images, and identify handwritten digits through image processing using convolution and neural networks.

Discover how supervised learning uses labeled data to train a model on historical features and labels, enabling predictions for new data such as gender from height.

Explore unsupervised learning by analyzing data without labels to discover structure and patterns. See how similar data points cluster based on inherent features, illustrating discovery without explicit annotations.

Explore how machine learning tackles business problems, from reducing vehicle maintenance costs using census data to evaluating donation sponsorships for teachers and students and predicting steering angles from onboard images.

Analyze a dataset with two classes (positive and negative) to build a machine learning model that can predict failures proactively and reduce maintenance costs.

Analyze how a donor platform receives hundreds of thousands of classroom project proposals and uses natural language processing and supervised learning to automate screening and predict approvals.

Explore automatic music generation by teaching a model to predict the next character in ABC notation sequences from thousands of example tunes, creating artificial music.

Predict steering angles from on road images using supervised learning. Build and evaluate a labeled image dataset where each image maps to a steering angle.

Conclude with practical machine learning problem statements through a variety of examples to reinforce concepts in data science.

Explore why Python is the preferred language for machine learning, highlighting its open source nature, intuitive syntax, and rich libraries that support data science workflows.