3.101
Overview of the Machine Learning Pipeline

---

Objectives

Upon completion of this lesson, you will be able to:

• list the steps in machine learning
• define machine learning
• distinguish between supervised and unsupervised algorithms

---

Introduction

Machine learning is a subfield of artificial intelligence that involves the development of algorithms that allow computers to learn patterns and make decisions from data. It is generally classified into two main types: Supervised Learning and Unsupervised Learning.

1. Supervised Learning: This involves using labeled training data to train a model to make predictions. In supervised learning, each example in the training dataset consists of an input vector and its corresponding output value (the label). The goal is to create a model that maps inputs to outputs for future predictions. This is typically used in tasks such as classification (where the output is discrete, such as identifying whether an email is spam or not spam) and regression (where the output is continuous, like predicting house prices).

2. Unsupervised Learning: In contrast, unsupervised learning involves training a model using data that has not been labeled. The model is left to find patterns and relationships within the data on its own. The most common unsupervised learning tasks are clustering (grouping similar instances together), anomaly detection (identifying unusual instances), dimensionality reduction (simplifying the input without losing too much information), and association rule learning (discovering interesting relations between attributes).

As for the applications, here are some examples for each:

Supervised Learning Applications:

• Image classification: Identifying the category of an object in an image.
• Speech recognition: Converting spoken language into written form.
• Email spam filtering: Classifying emails as spam or not spam.
• Predictive modeling: Predicting future events such as sales or stock prices.

Unsupervised Learning Applications:

• Customer segmentation: Grouping customers into clusters based on their purchasing behavior.
• Anomaly detection: Identifying fraudulent transactions in credit card usage.
• Recommender systems: Providing product recommendations based on user behavior patterns.
• Topic modeling: Identifying the main topics in a large collection of documents.

Naturally these are broad categories, and many machine learning tasks involve aspects of both supervised and unsupervised learning, as well as other types such as semi-supervised learning and reinforcement learning.

Tutorial

In this narrated slide presentation, Dr. Schedlbauer of Khoury Boston provides an overview of machine learning and the pipeline that most machine learning projects follow.

---

Files & Resources

All Files for Lesson 3.101

---

References

No references.

Errata

None collected yet. Let us know.