Understanding AI Fundamentals

Introduction to AI

• Artificial Intelligence (AI) refers to the development of computer systems that can perform tasks that typically require human intelligence.
• Two primary approaches to AI programming: rule-based programming and data-driven programming.

Types of AI

• Machine Learning (ML): a subset of AI that enables machines to learn from data without being explicitly programmed.
• Narrow or Weak AI: designed to perform a specific task, such as facial recognition or language translation.
• General or Strong AI: hypothetical AI that possesses human-like intelligence and can perform any intellectual task.

Machine Learning Types

• Supervised Learning: trained on labeled data to learn patterns and make predictions.
• Unsupervised Learning: trained on unlabeled data to discover patterns and relationships.
• Reinforcement Learning: learns through trial and error by receiving rewards or penalties.
• Semi-Supervised Learning: combination of supervised and unsupervised learning.

AI Lifecycle

• Defining the problem: identifying a problem or opportunity that AI can solve.
• Preparing Data: collecting, cleaning, and preprocessing data for model training.
• Training: using data to train and develop an AI model.
• Testing: evaluating the performance of the trained model.
• Evaluating the Model: assessing the model's accuracy, confidence, and bias.

Machine Learning: Data Preparation

• Data Cleaning: handling duplicates, missing data, and invalid data to ensure data quality.

Machine Learning: Testing

• Testing for Bias: identifying and mitigating biases in the model to ensure fairness.
• Measuring Accuracy and Confidence: evaluating the model's performance and predicting uncertainty.

Decision Trees

• A decision tree is a graphical representation of decisions and their consequences, including chance node events and utility node payoffs.
• Decision trees can be used to solve problems with ML models by identifying the most important features and relationships in the data.

Bias in Machine Learning

• Bias in, Bias out: the concept that biased data leads to biased models and predictions.
• Importance of addressing bias in ML models to ensure fairness and accuracy.