Python Based

Basic Machine Learning

Dr. –Ing. Youjin Kim
인문대학2호관 331
1:00pm ~
Semester & Evaluation Plan
• Midterm 35%, Final 35%
• Attendance & Assignment 20% Attitude 10%

Attendance Rule
• Absence Excuse accepted with the official letter of absence
Official letter inquiry? To Student Assistant (Office)
Absences with sickness, Visa issue, personal matters…. No acceptance
• ¼ absence = Fail
Semester & Evaluation Plan
• Midterm 35%, Final 35%
• Attendance 10% Assignment 20% Attitude 10%

Time Table
1:00 ~ 2:00 Theory 1 & Student Activity
2:00 ~ 3:00 Theory 2 & Student Activity (CoLab)
3:00 ~ 3:30 Self study for Student Activities
Semester & Evaluation Plan
• No Class 10/3
• Video Class 10/10 (Plan)
• Mid-Term 10/31
Lecture Objectives
1. Understand the fundamentals of AI, big data, and machine
learning concepts.
2. Develop proficiency in Python programming for data analysis
and machine learning.
3. Apply learned skills to real-world data analysis projects and
machine learning applications.
Lecture Description
*Basic computing skill and Linear Algebra (2024-1 LA toward
AI course) knowledges are essential to take this course.*
• This course provides a comprehensive introduction to AI, big
data, and machine learning using Python.
• Over 15 weeks, students will learn essential programming skills,
data analysis techniques, and practical applications of machine
learning through a blend of theoretical lectures and hands-on
coding exercises.
• By the end of the course, students will be equipped to analyze
data, implement machine learning models, and tackle real-world
problems using Python.
Lecture 1
• Introduction to AI and Big Data
• Computational Thinking, Logical Thinking, Designing Algorithm
• Basic Python Setup and Introduction using Colab
• Writing Simple Python Programs
Artificial Intelligence (AI)
• Artificial intelligence (AI) is technology that enables
computers and machines to simulate human learning,
comprehension, problem solving, decision making,
creativity and autonomy.
• Applications and devices equipped with AI can see and
identify objects.
They can understand and respond to human language.
They can learn from new information and experience. Image AI translation advances are now posing a risk to jobs - Verdict

• They can make detailed recommendations to users

and experts. They can act independently, replacing the
need for human intelligence or intervention (a classic
example being a self-driving car).
What Is Artificial Intelligence (AI)? | IBM

Image WVU researcher to study computer vision-related image recognition | WVU Today | West Virginia University
Artificial Intelligence (AI)

Image: Artificial Intelligence - SwissCognitive – The Global AI Hub

Evolution of AI
• A simple way to think about AI is as a series of nested or derivative
concepts that have emerged over more than 70 years:

What Is Artificial Intelligence (AI)? | IBM

What Is Artificial Intelligence (AI)? | IBM

Machine Learning (ML)

• It involves creating models by training an algorithm to make predictions or
decisions based on data. It encompasses a broad range of techniques that
enable computers to learn from and make inferences based on data
without being explicitly programmed for specific tasks.
• Types of ML : linear regression, logistic regression, decision trees, random
forest, support vector machines (SVMs), k-nearest neighbor
(KNN), clustering and more.

Image: Deep Learning vs Machine Learning: The Ultimate Battle. (turing.com)

What Is Artificial Intelligence (AI)? | IBM

Machine Learning
• But one of the most popular types of is called Neural Network.
Neural networks are modeled after the human brain's structure and
function.
• A neural network consists of interconnected layers of nodes (analogous to
neurons) that work together to process and analyze complex data. Neural
networks are well suited to tasks that involve identifying complex patterns
and relationships in large amounts of data.

Get an Overview of Neuron Cells- CUSABIO Image: Artificial Neural Networks and its Applications - GeeksforGeeks
What Is Artificial Intelligence (AI)? | IBM

Machine Learning
• The simplest form of machine learning is called supervised learning, which
involves the use of labeled data sets to train algorithms to classify data or
predict outcomes accurately. In supervised learning, humans pair each
training example with an output label. The goal is for the model to learn the
mapping between inputs and outputs in the training data, so it can predict
the labels of new, unseen data.

지도 학습과 비지도 학습 - GeeksforGeeks

So what is a neural network? | 3Blue1Brown

• https://www.youtube.com/watch?v=aircAruvnKk&t=5s
• 1:08 Preview
• 2:45 Neuron?
• 3:35 Introducing Layers
• 5:30 Why Layers?
What Is Artificial Intelligence (AI)? | IBM

Deep Learning
• Deep learning is a subset of machine learning that uses multilayered
neural networks, called deep neural networks, that more closely simulate
the complex decision-making power of the human brain.
• Deep neural networks include an input layer, at least three but usually
hundreds of hidden layers, and an output layer, unlike neural networks
used in classic machine learning models, which usually have only one or
two hidden layers.

Image: Deep Learning vs Machine Learning: The Ultimate Battle. (turing.com)

Image: Deep Learning vs Machine Learning: The Ultimate Battle. (turing.com)
What Is Artificial Intelligence (AI)? | IBM

Deep Learning
• These multiple layers enable unsupervised learning: they can automate the extraction of
features from large, unlabeled and unstructured data sets, and make their own predictions
about what the data represents.
• Because deep learning doesn’t require human intervention, it enables machine learning at
a tremendous scale. It is well suited to natural language processing (NLP), computer
vision, and other tasks that involve the fast, accurate identification complex patterns and
relationships in large amounts of data. Some form of deep learning powers most of the
artificial intelligence (AI) applications in our lives today.

지도 학습과 비지도 학습 - GeeksforGeeks

Computational Thinking
• ‘Computational thinking is the thought processes involved in
formulating a problem and expressing its solution(s) in such a
way that a computer—human or machine—can effectively carry
out.’
Jeanette Wing, 2014
Computational Thinking
Source Definition
Wing, 2014 ‘Computational thinking is the thought processes involved in formulating
a problem and expressing its solution(s) in such a way that a
computer—human or machine—can effectively carry out.’

Yadav et al., ‘The mental activity for abstracting problems and formulating solutions
2014 that can be automated.’
Furber, 2012 ‘The process of recognizing aspects of computation in the world that
surrounds us, and applying tools and techniques from Computer
Science to understand and reason about both natural and artificial
systems and processes.’
 Computing
- the skills and practices in both computer science
and computational thinking.

Computational thinking
- a problem-solving approach that
- integrates across activities, and

Computer science
- Individual academic discipline

Programming
- The practice of developing a set of instructions
- for a computer can understand and execute
- debugging, organizing, and applying that code to
appropriate problem-solving contexts.
https://digitalpromise.org/initiative/computational-
thinking/computational-thinking-for-next-generation-science/what-
is-computational-thinking/
Computational Thinking Computer Science
- Broader concept - The study and application of
- Thinking like computer the principles of mathematical
scientist (Jeanette Wing) computation
- An approach to problem- - Subfield : programming
solving - Focuses on the production of
- CT assumes a computer high-quality software
will execute the eventual
solution

https://digitalpromise.org/initiative/computational-thinking/computational-thinking-
for-next-generation-science/what-is-computational-thinking/
Beecher, Karl. Computational Thinking: A beginner's guide to
problem-solving and programming. BCS Learning &
Development Limited. Kindle Edition.

Beecher, Karl. Computational Thinking: A beginner's guide to problem-solving and programming. BCS Learning & Development Limited. Kindle Edition.
Computational Thinking Steps
Algorithmic Thinking
• An algorithm is a sequence of logical instructions for carrying
out a task. In computing, algorithms are needed to design
computer programs.

Flowcharts - Digital design principles - CCEA - GCSE Digital Technology (CCEA) Revision - BBC Bitesize
Algorithmic Thinking
• We can use flowcharts to plan and demonstrate the flow of data
in a solution. They help us visualize what is going on.

Flowcharts - Digital design principles - CCEA - GCSE Digital Technology (CCEA) Revision - BBC Bitesize
Colab Page Creation
• Colab is a hosted Jupyter Notebook service that requires no
setup to use and provides free access to computing resources,
including GPUs and TPUs. Colab is especially well suited to
machine learning, data science, and education.
• The document you are reading is not a static web page, but an
interactive environment called a Colab notebook that lets you
write and execute code.
• https://colab.research.google.com/
Basic Code Explaination
• Import numpy: Call Python library for numeric calculation
• vector_a and vector_b are simple 1D arrays
• matrix_ a and matrix_b are 2D arrays.
• Operations:
We perform vector addition
and matrix multiplication.
• Print: Show the values of the above input
values.
Copy the link and put it on the comment of the Lecture 1 in LMS