4.25 (1938 reviews)
☑ You'll be familiar with many of the basic algorithms used in machine learning.
☑ You'll have solid understanding of how real world models are built using Python.
☑ You'll know exactly what machine learning is and what it isn't.
☑ You'll be prepared for the machine learning questions on the Google Certified Data Engineering Exam.
THE REVIEWS ARE IN:
Another Excellent course from a brilliant Instructor. Really well explained, and precisely the right amount of information. Mike provides clear and concise explanations and has a deep subject knowledge of Google's Cloud. -- Julie Johnson
Awesome! -- Satendra
Great learning experience!! -- Lakshminarayana
Wonderful learning... -- Rajesh
Excellent -- Dipthi
Clear and to the point. Fit's a lot of knowledge into short, easy to understand concepts/thoughts/scenarios. -- Sam
Course was fantastic. -- Narsh
Great overview of ML -- Eli
Very helpful for beginners, All concept explained well. Overall insightful training session. Thank you ! --Vikas
Very good training. Concepts were well explained. -- Jose
I like the real world touch given to course material . This is extremely important. -- Soham
Learned some new terms and stuffs in Machine Learning. Ideal for learners who needs to get some overview of ML. -- Akilan
This session is very good and giving more knowledge about machine learning -- Neethu
Got to know many things on machine learning with data as a beginner. Thanks Mike. --Velumani
Really well explained and very informative. -- Vinoth
Welcome to An Introduction to Machine Learning for Data Engineers. This course is part of my series for data engineering. The course is a prerequisite for my course titled Tensorflow on the Google Cloud Platform for Data Engineers.
This course will show you the basics of machine learning for data engineers. The course is geared towards answering questions for the Google Certified Data Engineering exam.
This is NOT a general course or introduction to machine learning. This is a very focused course for learning the concepts you'll need to know to pass the Google Certified Data Engineering Exam.
At this juncture, the Google Certified Data Engineer is the only real world certification for data and machine learning engineers.
Machine learning is a type of artificial intelligence (AI) that allows software applications to become more accurate in predicting outcomes without being explicitly programmed. The key part of that definition is “without being explicitly programmed.”
The vast majority of applied machine learning is supervised machine learning. The word applied means you build models in the real world. Supervised machine learning is a type of machine learning that involves building models from data that exists.
A good way to think about supervised machine learning is: If you can get your data into a tabular format, like that of an excel spreadsheet, then most machine learning models can model it.
In the course, we’ll learn the different types of algorithms used. We will also cover the nomenclature specific to machine learning. Every discipline has their own vernacular and data science is not different.
You’ll also learn why the Python programming language has emerged as the gold standard for building real world machine learning models.
Additionally, we will write a simple neural network and walk through the process and the code step by step. Understanding the code won't be as important as understanding the importance and effectiveness of one simple artificial neuron.
*Five Reasons to take this Course.*
1) You Want to be a Data Engineer
It's the number one job in the world. (not just within the computer space) The growth potential career wise is second to none. You want the freedom to move anywhere you'd like. You want to be compensated for your efforts. You want to be able to work remotely. The list of benefits goes on.
2) The Google Certified Data Engineer
Google is always ahead of the game. If you were to look back at a timeline of their accomplishments in the data space you might believe they have a crystal ball. They've been a decade ahead of everyone. Now, they are the first and the only cloud vendor to have a data engineering certification. With their track record I'll go with Google.
3) The Growth of Data is Insane
Ninety percent of all the world's data has been created in the last two years. Business around the world generate approximately 450 billion transactions a day. The amount of data collected by all organizations is approximately 2.5 Exabytes a day. That number doubles every month.
4) Machine Learning in Plain English
Machine learning is one of the hottest careers on the planet and understanding the basics is required to attaining a job as a data engineer. Google expects data engineers to be able to build machine learning models. In this course, we will cover all the basics of machine learning at a very high level.
5) You want to be ahead of the Curve
The data engineer role is fairly new. While you’re learning, building your skills and becoming certified you are also the first to be part of this burgeoning field. You know that the first to be certified means the first to be hired and first to receive the top compensation package.
Thanks for your interest in An Introduction to Machine Learning for Data Engineers.
Is this Course for You?
Machine Learning Defined
Machine Learning Types
The Modeling Process
Model Building in Python
Why Applied Machine Learning is Mostly Python
Creating Datalab Notebooks on Google's Cloud Platform
Cloud Datalab Notebook Navigation
Lab: Creating Our Datalab Virtual Machine
Data Massaging Introduction
Lesson Speed Warning
Using Pandas to Massage Data - Data Structures
Using Pandas to Massage Data - Data Frame
Lab: Working with Dataframes
Machine Learning algorithms
Support Vector Machines
Google Sample Questions
Building a Single Perceptron Model
Model Building with 1 Perceptron
The Perceptron Code
Linear Function Code
The Entire Perceptron Model
Neural Networks in Under Ten Minutes
Lab: A Simple Neural Network in TensorFlow
Overfitting and How to Correct it
Lab: Pick the Features that Matter
Feature Engineering Lab Review
Bonus Lecture: An Introduction to Data Engineering
I just covered 1st chapter, explanation is not clear, there are lot of spelling or sentence making mistakes, the quiz questions are not related/relevant to the course material covered.
Good course that covers quickly lots of essential concepts, but would be better to just slightly put them more in perspective toward each others. After all, it's a course for beginners. Fixing the slides instead of "this is an error" disclaimer would be nice.
The course content is good but the trainer is very fast in communication ;few areas I felt difficult to follow him
clear and to the point. Fit's a lot of knowledge into short, easy to understand concepts/thoughts/scenarios. the Datalab setup falls very short though. There are missing critical steps.
a little slow and makes the topic seem boring. the handwriting is not very clear and could be replaced by a slightly more professional animation
Halfway in the course (section 5). the code change from Python to none-python (not sure what program is that).
So far, so good. In the explanation of Modeling Process, I expected to hear explicitly about Training, which I presumed is implicit to the "Build the model" box.
A good intro to the topic. But to pass the exam you need to dive much deeper to every single piece of detail, including troubleshooting and choosing the best option out of several possible options.
Light & nice intro into a complex topics. Mike cleared many misconceptions I had, & greatly simplified the concepts.
Well I learned a lot! It pulled together a lot of knowledge that I already had but never attributed it to machine learning. So far it sounds like fun. My only criticism was that I couldn't get to the cloud platform, I did read that after the $300 Google credit that one would be paying by the second, it didn't say how much per second - that was scary, and I noticed some price tags of over $2000. That's not your fault I realize but it puts the brakes on a bit. I am glad you continued to explain other things which did not require the cloud. But, in summary, your lectures were excellent.
The course is a quick overview of ML. The most useful outcome for me was that it made me set up a Google Cloud account and figure out how to set up a Jupyter notebook in Datalab. The course is very short and basic, without any direct practical application. The quizes are pretty bad.
This overview of machine learning is really a very light OVERVIEW. The explanations are clear and the summary pages are useful but I got very frustrated that the topics were dealt with in such a superficial manner. For instance, I was pretty excited by the content of section 5 where we are blessed to take a sneak peek at the code of the Perceptron model, but this goes too fast, no real analysis of the code is provided… I guess all this frustration is the trade off that comes with the 70 minute format!... A few of the quiz questions seem unintelligent, i.e. they don’t check at all that a particular concept has been understood.
Overall great and concise course on the introduction to Machine Learning. It's meant as an introduction, so use this course just to get an overview, and dig into more in-depth courses.
The objectives are very clear from the beginning. Voice is calm but confident. The speaker focuses on the correct topics. Looks like a fun course where I'll learn a lot!
So far i had a good understanding of the process involved in getting to the Predictive Model from the raw data