Quick Notes - DOMAIN 2: AWS Certified AI Practitioner

If you are prepping for the AWS Certified AI Practitioner https://aws.amazon.com/certification/certified-ai-practitioner/, these notes should be enough to get the fundamentals for the exam.

Domain 2: Exploring Artificial Intelligence Use Cases and Applications

AI applications and other AWS services automate processes across various industries. Some of the applications include computer vision, natural language processing (NLP), intelligent document processing (IDP), and fraud detection.

• Computer vision is a field of artificial intelligence that allows computers to interpret and understand digital images and videos. Deep learning has revolutionized computer vision by providing powerful techniques for tasks such as image classification, object detection, and image segmentation.

• NLP is a branch of artificial intelligence that deals with the interaction between computers and human languages.

• IDP is an application that extracts and classifies information from unstructured or structured data, generates summaries, and provides actionable insights.

• Fraud detection is an AI application that identifies and prevents fraudulent activities, such as credit card fraud or cybersecurity threats.

  
  

Machine Learning:

ML learning techniques represent the backbone of modern AI and empower systems to learn from data and make intelligent decisions without explicit programming.

• Supervised Learning - the algorithms are trained on labeled data.

  • Classification is a supervised learning technique used to assign labels or categories to new, unseen data instances based on a trained model.

    • Use cases include the following:

      • Fraud detection

      • Image classification

      • Customer retention

      • Diagnostics

  • Regression is a supervised learning technique used for predicting continuous or numerical values based on one or more input variable.

    • Use cases include the following:

      • Advertising popularity prediction

      • Weather forecasting

      • Market forecasting

      • Estimating life expectancy

      • Population growth prediction

• Unsupervised Learning - labels are not provided—you don't know all the variables and patterns.

A common subcategory of unsupervised learning is clustering. This kind of algorithm groups data into different clusters based on similar features or distances between the data point to better understand the attributes of a specific cluster.

Dimensionality reduction is an unsupervised learning technique used to reduce the number of features or dimensions in a dataset while preserving the most important information or patterns.

• Reinforcement Learning - this one continuously improves its model by mining feedback from previous iterations. In reinforcement learning, an agent continuously learns through trial and error as it interacts in an environment.

Note: Linear regression models are highly interpretable because the model's coefficients directly represent the relationship between each feature and the target variable. Therefore, linear regression models provide a clear understanding of how the model arrives at its predictions.

Generative AI

Challenges:

• Nondeterminism is a challenge where the model produces different outputs each time it runs with the same input data.

• Toxicity occurs when the model is generating content that is inflammatory, offensive, or inappropriate.

• Social risks occur when the model generates unwanted content that might negatively affect your organization.

• Hallucinations occur when the model generates inaccurate responses that are not consistent with the training data.

For Domain 3 -> https://www.bansalonsecurity.com/post/quick-notes-domain-3-aws-certified-ai-practitioner

Reference: AWS SkillBuilder https://skillbuilder.aws/learn