L2: Deep Learning and Machine Learning

Definition

Collections of small computing units (neurons) that process data and learn to make decisions over time.

A statistical technique that uses Bayes’ theorem to update probabilities based on new evidence.

Accurate insights and reports generated by generative AI can be updated as data evolves, enhancing decision-making and uncovering hidden patterns.

The process of grouping similar data points together based on certain features or attributes.

Using generative AI to automatically generate and test software code for constructing analytical models, freeing data scientists to focus on higher-level tasks.

The process of automatically searching and analyzing data to discover patterns and insights that were previously unknown.

A type of machine learning algorithm used for decision-making by creating a tree-like structure of decisions.

Includes Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) that create new data instances by learning patterns from large datasets.

Characteristics used to describe big data: Velocity, volume, variety, veracity, and value.

A subset of AI that focuses on creating new data, such as images, music, text, or code, rather than just analyzing existing data.

Analyzing which goods tend to be bought together is often used for marketing insights.

A simple probabilistic classification algorithm based on Bayes’ theorem.

A field of AI that enables machines to understand, generate, and interact with human language, revolutionizing content creation and chatbots.

Metrics are used to evaluate the performance of classification models.

Using machine learning techniques to predict future outcomes or events.

Artificially generated data with properties similar to real data, used by data scientists to augment their datasets and improve model training.