The document provides an introduction to machine learning, defining it as the ability of a computer program to improve performance on specific tasks through experience. It outlines the types of learning: supervised, unsupervised, and reinforcement learning, along with examples and methodologies such as regression and classification models. Key concepts include the use of labeled and unlabeled data, and the goal of discovering patterns or predicting outcomes.

1. Introduction to Machine Learning

2. Motivation

3. Definition
A computer program is said to learn from experience E with respect to some class of
tasks T and performance measure P, if its performance at tasks in T, as measured by
P, improves with experience E.
Example: Handwritten Digit Recognition
T: Classifying handwritten digits from images
P: Percentage of digits classified correctly
E: Dataset of digits given classification (MNIST)

4. A Little History

5. Types
1. Supervised Learning - Labeled Data, Direct Feedback, Predict Outcome/Future
2. Unsupervised Learning - Unlabeled Data, No Feedback, Find Hidden Structure in
Data
3. Reinforcement Learning - Decision Process, Reward System, Learn Series of Actions

6. Outline
1. Supervised Learning
a. Regression Models
b. Classification Models
i. Decision Trees
ii. Perceptron
iii. Neural Networks
2. Unsupervised Learning
a. Clustering