Introduction to Machine Learning

Focused View

5:42:04

0 View

1 - Introduction

1 -Welcome.mp4

03:58

2 - Data Pipelines

1 -Outline.mp4

04:49

1 -kaggle machine learning competitions.zip

2 -Data Collection.mp4

16:25

3 -Explorative Analysis.mp4

24:26

3 -google facets.zip

4 -Data Cleaning.mp4

13:21

5 -Data Preparation.mp4

07:19

6 -Dimensionality Reduction.mp4

08:31

6 -principal component analysis visualization.zip

7 -Feature Engineering.mp4

05:38

3 - Machine Learning Taxonomy and Supervised Learning

1 -Introducing machine learning.mp4

20:52

1 -chatgpt.zip

1 -gooey animation ai.zip

1 -openart image ai.zip

1 -suno music ai.zip

2 -Machine Learning Taxonomy.mp4

19:00

3 -Regression Models.mp4

11:55

3 -interactive visualization of linear regression.zip

4 -Support Vector Machines.mp4

11:46

4 -interactive visualization of svms.zip

5 -K-Nearest Neighbours.mp4

04:17

6 -Decision Trees.mp4

07:32

7 -Tree-based Ensembles.mp4

11:55

4 - Unsupervised Learning

1 -K-Means.mp4

11:17

2 -Hierarchical Clustering.mp4

06:31

3 -Gaussian Mixture Models.mp4

10:08

4 -DBSCAN.mp4

06:46

5 - Deep Learning

1 -Introduction.mp4

02:17

2 -Perceptron.mp4

01:12

3 -Artificial Neural Networks.mp4

08:01

4 -Convolutional Neural Networks.mp4

10:36

4 -visualization of features extracted by different cnn layers.zip

5 -Recurrent Neural Networks.mp4

09:59

6 -Autoencoders.mp4

10:48

6 -blogpost discussing checkerboarding artefacts in transpose convolutions.zip

6 - Practical demonstrations

1 -Data Exploration Demonstration.mp4

19:33

2 -Basic Breast Cancer Dataset Example.mp4

36:05

3 -Estimated Time of Arrival Demonstration.mp4

37:07

Description

A beginners guide to commonly used machine learning models and terminology

What You'll Learn?

Define the fundamental aspects of data pipelines that is necessary for machine learning
Identify the potential pitfalls when building data pipelines
Recognize the different types of machine learning models and explain their differences
Discuss popular supervised machine learning models
Understand popular unsupervised clustering algorithms
Broadly define what neural networks are
Know what some of the most popular neural network variants are and when to use them
Utilize machine learning fundamentals to implement basic solutions to classification and regression problems

Who is this for?

Software engineers that want to be able to follow discussions about the machine learning pipeline

Managers that are looking to incorporate machine learning into their business and want to better understand the intricacies of doing so

Prospective students that want to establish whether machine learning is the right field for them

This course is not intended for learners with prior machine learning knowledge

This course is not intended for learners that wants to understand the mathematical foundations of machine learning

What You Need to Know?

Some programming experience will be beneficial for exercises and examples, but is not required.

More details

Description
This course aims to provide students with a broad overview of the field of machine learning and will introduce some important terms and techniques which will enable them to follow a discussion on the topic. I will discuss the fundamental aspects of data pipelines and will point out what some of the common pitfalls are when preparing data for a machine learning project. I will also discuss what the different types of machine learning models are and how they differ from deep learning models.

Broad overviews will be provided of some of the most popular supervised and unsupervised models and students will be introduced to some of the popular neural network variants. This will be followed by a few practical demonstrations which will show students how they can combine the discussed topics to create basic machine learning solutions.

This course will not provide in-depth explanations regarding the mathematical underpinnings of these models, nor will it provide detailed discussions regarding how to implement machine learning models from scratch. Instead, the aim is to simplify and condense the subject matter to provide students with an easily digestible introduction to the field.

Whether students are employers or employees, we believe it to be highly beneficial to have a basic understanding of what machine learning models are and what they are not --- especially as machine learning tools become increasingly common in many domains.
Who this course is for:
Software engineers that want to be able to follow discussions about the machine learning pipeline
Managers that are looking to incorporate machine learning into their business and want to better understand the intricacies of doing so
Prospective students that want to establish whether machine learning is the right field for them
This course is not intended for learners with prior machine learning knowledge
This course is not intended for learners that wants to understand the mathematical foundations of machine learning

User Reviews

Rating

average 0

Total votes0

Focused display

Machine Learning

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.