INTRODUCTION TO

MACHINE LEARNING
Ariana Villegas
 ➔ Hello, I'm Ariana Villegas!

➔ I studied my undergraduate degree in

Computer Science at UTEC from 2018 to
2023.

➔ I earned my Master's degree in Computer

Science at the University of New Mexico in
Spring 2024.

➔ I have conducted research in various areas,

including computer vision, reinforcement
ABOUT ME

learning, and temporal analysis.

➔ Outside of research, I'm usually reading,

climbing or playing tennis.
 ➔ Topics covered: Supervised Learning
(Regression and Classification), Feature
Extraction, Dimensionality Reduction,
Unsupervised Learning (Clustering), Neural
Networks (MLP, CNN, RNN) and
Reinforcement Learning (Multi Arm Bandit)

➔ This class assume knowledge of

programming (such as python), probability
ABOUT CLASS

and statistics (such as probability theory

and random processes), linear algebra and
calculus.

➔ You are wasting your time here if you

haven’t had the prereq material. Like sitting
in on a Japanese III class if you haven’t
taken Japanese I and II.
 ADMINISTRIVIA
WEEK TUESDAY WEDNESDAY FRIDAY TOPIC

1 25/03/2025 26/03/2025 28/03/2025 Introduction

2 01/04/2025 02/04/2025 04/04/2025 Regression
3 08/04/2025 09/04/2025 11/04/2025 Regression
4 15/04/2025 16/04/2025 18/04/2025 Classification
5 22/04/2025 23/04/2025 25/04/2025 Classification Prereq Quiz
6 29/04/2025 30/04/2025 02/05/2025 Classification
7 06/05/2025 07/05/2025 09/05/2025 Dimensionality Reduction Project Out
8 13/05/2025 14/05/2025 16/05/2025 Dimensionality Reduction
9 20/05/2025 21/05/2025 23/05/2025 Clustering Project Deadline
10 27/05/2025 28/05/2025 30/05/2025 Clustering
Midterm + Final
11 03/06/2025 04/06/2025 06/06/2025 Clustering
12 10/06/2025 11/06/2025 13/06/2025 Neural Networks
13 17/06/2025 18/06/2025 20/06/2025 Neural Networks
14 24/06/2025 25/06/2025 27/06/2025 Reinforcement learning
15 01/07/2025 02/07/2025 04/07/2025 Reinforcement learning
16 08/07/2025 09/07/2025 11/07/2025 Final Presentations
 ADMINISTRIVIA
WEEK TUESDAY WEDNESDAY FRIDAY TOPIC
Final Grade = Project 1 (10%)
1 25/03/2025 26/03/2025 28/03/2025 Introduction
2 01/04/2025 02/04/2025 04/04/2025 Regression + Project 2 (10%)
3 08/04/2025 09/04/2025 11/04/2025 Regression
+ Project 3 (20%)
4 15/04/2025 16/04/2025 18/04/2025 Classification
5 22/04/2025 23/04/2025 25/04/2025 Classification + Midterm (10%)
6 29/04/2025 30/04/2025 02/05/2025 Classification
7 06/05/2025 07/05/2025 09/05/2025 Dimensionality Reduction
+ Final (20%)
8 13/05/2025 14/05/2025 16/05/2025 Dimensionality Reduction
+ EC1 (15%)
9 20/05/2025 21/05/2025 23/05/2025 Clustering
10 27/05/2025 28/05/2025 30/05/2025 Clustering + EC2 (15%)
11 03/06/2025 04/06/2025 06/06/2025 Clustering
12 10/06/2025 11/06/2025 13/06/2025 Neural Networks
EC1 = Quiz + Labs
13 17/06/2025 18/06/2025 20/06/2025 Neural Networks
14 24/06/2025 25/06/2025 27/06/2025 Reinforcement learning EC2 = Labs
15 01/07/2025 02/07/2025 04/07/2025 Reinforcement learning
16 08/07/2025 09/07/2025 11/07/2025 Final Presentations Theory Practice
 ADMINISTRIVIA
WEEK TUESDAY WEDNESDAY FRIDAY TOPIC

1 25/03/2025 26/03/2025 28/03/2025 Introduction => Projects: 3 or 4 people per group

2 01/04/2025 02/04/2025 04/04/2025 Regression
3 08/04/2025 09/04/2025 11/04/2025 Regression => Random Groups (P1)
4 15/04/2025 16/04/2025 18/04/2025 Classification
5 22/04/2025 23/04/2025 25/04/2025 Classification
=> Random Weighted Groups (P2)
6 29/04/2025 30/04/2025 02/05/2025 Classification
=> Student-Chosen Groups (P3)
7 06/05/2025 07/05/2025 09/05/2025 Dimensionality Reduction
8 13/05/2025 14/05/2025 16/05/2025 Dimensionality Reduction
9 20/05/2025 21/05/2025 23/05/2025 Clustering
Weights = Labs (60%) + Prev Project (40%)
10 27/05/2025 28/05/2025 30/05/2025 Clustering
11 03/06/2025 04/06/2025 06/06/2025 Clustering Project = Part1 (30%) + Part2 (70%)
12 10/06/2025 11/06/2025 13/06/2025 Neural Networks
13 17/06/2025 18/06/2025 20/06/2025 Neural Networks Part1 = Proofs, derivations, …
14 24/06/2025 25/06/2025 27/06/2025 Reinforcement learning
15 01/07/2025 02/07/2025 04/07/2025 Reinforcement learning
Part2 = Problem solving …
16 08/07/2025 09/07/2025 11/07/2025 Final Presentations
 RESOURCES
Prerequisites

➔ There's a fantastic collection of linear algebra visualizations on YouTube by 3Blue1Brown (Grant Sanderson) starting with this
playlist, The Essence of Linear Algebra. I highly recommend them, even if you think you already understand linear algebra.
It's not enough to know how to work with matrix algebra equations; it's equally important to have a geometric intuition for
what it all means.

➔ Here's a short summary of math for machine learning written by Garrett Thomas.

➔ Stanford's machine learning class provides additional reviews of linear algebra and probability theory.

Machine Learning Class

➔ Pattern Recognition and Machine Learning, Christopher Bishop

➔ Machine Learning, Tom Mitchell.

➔ Machine Learning: a Probabilistic Perspective, Kevin Murphy.

➔ *A Course in Machine Learning, Hal Daumé III. Online only.

➔ An Introduction to Statistical Learning with Applications in R, Gareth James, Daniela Witten, Trevor Hastie
 CONTACT
Email: [email protected]

AVOID [email protected]
 FAQ

➔ What is the setup for quizzes, midterms, and finals?

Students are responsible for ensuring they are prepared to take exams using Proctorio, with a stable
internet connection. If you cannot meet these conditions, please contact the professor in advance.

➔ Are extensions available for projects?

Project deadlines are typically firm, but extensions may be granted under special circumstances.

➔ Are there opportunities for extra points or makeup work?

There are no official extra points or makeup assignments for exams or projects. However, extra points
may be awarded for work that goes beyond the project’s scope.

➔ What should I do if my group isn't responding to me?

Notify the professor as soon as possible so that appropriate arrangements can be made.
 FAQ

➔ I’d prefer not to learn how to build interesting machine learning models, and would rather have
an interesting model do it for me. Can I just have an LLM write my code for me?

No! One of the key learning outcomes of this course is that you will be able to debug broken machine
learning code. We’ve found that one of the best ways to provide you with broken machine learning
code is to let you write it yourself.
WHO ARE WE?
https://www.menti.com/alipgnqyx9su
 WHAT IS
MACHINE LEARNING?
 What is Machine Learning?
How can we solve a specific problem?

As computer scientists we write a program that encodes a set of rules that are useful
to solve the problem

How can we
make a robot
cook?
 What is Machine Learning?
How can we solve a specific problem?

As computer scientists we write a program that encodes a set of rules that are useful
to solve the problem

In many cases is very difficult to specify those rules, e.g., given a picture determine
whether there is a cat in the image
 What is Machine Learning?
Learning systems are not directly programmed to solve a problem, instead develop own
program based on

Examples of how they should behave

From trial-and-error experience trying to solve the problem

Different than standard CS: Want to implement unknown function, only have access
e.g., to sample input-output pairs (training examples). Learning simply means
incorporating information from the training examples into the system.
Machine Learning (A long long time ago…)
Machine Learning (A short time ago…)
Tasks that requires machine learning
What makes a 2?
Tasks that requires machine learning
Robots cooking?
What is Machine Learning?
 Why use Learning?
➔ It is very hard to write programs that solve problems like recognizing a handwritten digit

◆ What distinguishes a 2 from a 7?

◆ How does our brain do it?

➔ Instead of writing a program by hand, we collect examples that specify the correct output
for a given input

➔ A machine learning algorithm then takes these examples and produces a program that
does the job

◆ The program produced by the learning algorithm may look very different from a typical
hand-written program. It may contain millions of numbers.

◆ If we do it right, the program works for new cases as well as the ones we trained it on.
Defining a Machine Learning Solution
Defining a Machine Learning Solution
Defining a Machine Learning Solution
AI vs ML vs DL
 Defining a Machine Learning Task
A computer program learns if its performance P, at some task T, improves with experience E.
 Defining a Machine Learning Task
A computer program learns if its performance P, at some task T, improves with experience E.
 Example of a Learning Problem
A computer program learns if its performance P, at some task T, improves with experience E.

Learning to respond to voice commands (Siri)

1. Task, T: predicting action from speech

2. Performance measure, P: percent of correct actions

taken in user pilot study

3. Experience, E: examples of (speech, action) pairs

Let's take on a challenge!

In-Class Exercise
1. Select a task, T
2. Identify performance measure, P
3. Identify experience, E
4. Report ideas back to rest of class