Scribd
Upload
9 views39 pages

Introduction to Machine Learning Basics

The document outlines an introductory course on Machine Learning (ML) and its applications, focusing on understanding ML and AI concepts, setting up Anaconda and Python, and basic Python functions. It covers different types of learning such as supervised, unsupervised, and semi-supervised learning, as well as the importance of data quality in ML processes. Additionally, it emphasizes the use of Python libraries for real-world applications in ML.

Uploaded by

lci16164
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views39 pages

Introduction to Machine Learning Basics

The document outlines an introductory course on Machine Learning (ML) and its applications, focusing on understanding ML and AI concepts, setting up Anaconda and Python, and basic Python functions. It covers different types of learning such as supervised, unsupervised, and semi-supervised learning, as well as the importance of data quality in ML processes. Additionally, it emphasizes the use of Python libraries for real-world applications in ML.

Uploaded by

lci16164
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Machine Learning and its Applications

Week 1: Introduction to Machine Learning


Urban Information Lab
Learning Objective
Textbook (Useful if you have one)

1. Understand general information regarding ML & AI

2. Set up Anaconda & Python

3. Understand basic functions in Python


Session 1
1. Understand general information regarding ML & AI
Human Learning?

1. We learn from the things that happen to use – our experiences

2. Learning new things by acquiring appropriate responses to the events

3. Learning applies both humans and animals

Machine Learning?

1. Field of study that gives computers the ability to learn without being explicitly
programmed (Arthur Samuel, 1959).
2. Algorithms that automatically detect patterns in data -> uncover patterns
3. Algorithms that improve their performance (P), at some task (T), with
experience €
Supervised Learning
(Most widely used)

1. Classification (e.g. spam filter)

2. Regressor

3. Recommendation System

4. Text Analysis

Unsupervised Learning

1. Clustering

2. Low-dimensional manifold

3. Topic modelling

4. Recommendation System
Semi-supervised Learning
(Also name in reinforcement learning)
It actually existed decade ago…
Historical
Empirical Inference
Historical
Empirical Inference
Then, why suddenly got attention?

1. Improve in computer technology (better graphic, GPU, etc)

2. Advent of Big Data

-> Able to train and test more sophisticated model

3. Python
ML Process (1)
ML Process (2) Step 1&2

1) Where do we get Big but with good density data?

2) How are we going to replace missing values?


-> Drop? Fill up? Optimization?
Good Data Density?
Good Data Density?
Good Data Density?
Paradox of AI
Session 2
2. Set up Anaconda & Python
[Link]
Set Up
Install Anaconda
Install jupyter notebook

(For week 1-3, we are


using jupyter notebook)

Install recent python

Google Colab is also useful

Code easily and link to terminal


After Installation
Why Python?
Computer scientists and smart people already coded for you
ML libraries

Real World Application


Computer scientists and smart people already coded for you
ML libraries

If you are in Frontier,


You will be working to
build up the codes

But, in application part,


You are duty is to
understand how libraries
apply and choose the
one that fits your RQ

Real World Application


pip install python3
Type: jupyter notebook in Anaconda Prompt
Click New -> Python3

You might also like