## The 7 steps of machine learning

How can we tell if a drink is beer or wine? Machine learning, of course! In this episode of Cloud AI Adventures, Yufeng walks through the 7 steps involved in applied machine learning.

The 7 Steps of Machine Learning article: https://goo.gl/XEo6i2

Watch more episodes of AI Adventures here: https://goo.gl/UC5usG

TensorFlow Playground: http://playground.tensorflow.org
Machine Learning Workflow: https://goo.gl/SwLnSz
Hands-on intro level lab Baseline: Data, ML, AI → http://bit.ly/2KoBF6Y
Qwiklabs: https://goo.gle/2RH89Kh

Want more machine learning? Subscribe to the channel: https://goo.gl/S0AS51

Source

### Comment List

November 14, 2020

Excellent!

November 14, 2020

November 14, 2020

People get this stuff wrong, trust me!

November 14, 2020

Useful. Thank you!

November 14, 2020

Good resource!!! thank you

November 14, 2020
November 14, 2020

Excellent overview and great example.

November 14, 2020

Excuse me, I would like to know from where or in which book I get the information of the 7 steps of automatic learning

November 14, 2020

Awesome presentation! Clean, short and sweet.

November 14, 2020

1. DATA COLLECTION/GATHERING:

+Collect features. e.g.:
1. Alcohol concentration.=>Hydrometer.
2. Color.=>Spectrometer.
+High quantity & quality of data needed.

2. DATA PREPARATION:

+Randomization.
+Visualizations.
+Data split: training+testing/evaluation.

3. CHOOSING A MODEL:

+Among many in the community today. e.g. tensor flow.

4. TRAINING MODEL:

+Example: y=m*x+b.
The only values I can adjust/train are: m & b.
+In machine learning, there many m's since there are many features. +These m's are denoted using a matrix referred 2 as w(weights).
+The b's are organized into another couple matrix referred 2 as b(biases).
+After training once & getting a prediction, adjust the weights, w & biases, b.

5. EVALUATION:

+Test model against data that has never been used 4 training.
+Representative of how the model would perform in real world.
+Great split ratio example: 80% training & 20% evaluation.

6. PARAMETER TUNING:

+Example of such a params:
1. The no. of epochs; the number of passes of the entire training dataset the machine learning algorithm has completed .
2. Learning rate; how far we shift the line of y=m*x+y in each step.
+The parameters are referred 2 as the HYPERPARAMETERS.
+Tuning is more of an art than a science. i.e. it's an experimental process depending on the specifics of:
1. My dataset.
2. Model.
3. Training process.

7. PREDICTION:

+Doing sth useful, for example, in this case answering the question on whether it's bear or wine.

November 14, 2020

this video is so simple yet so informative. good job Yufeng and google!

November 14, 2020

How about an algorithm that detects the movement pattern of spies (in tf2)? The one man who would have that software, would be a tf2 god.

no more sneaky trickstabs.

November 14, 2020

Data is new currency

November 14, 2020

Simply, the best !

November 14, 2020

Amazing and well explained the complex subject in a simple way for those who are new Beebe.
Thank you for sharing

November 14, 2020

Best book for ai and machine learning

November 14, 2020

Wine…

November 14, 2020

kill the background music!

November 14, 2020

This is simple and straightforward. Thanks

November 14, 2020

Can machine learning predict how likely it'll be that you become a machine learning engineer if you said in the past in algebra class "WhEn WiLl We EvEr UsE tHiS IrL?"

November 14, 2020

Thank you

November 14, 2020

Why all examples are alcohol based? !

November 14, 2020

..knowing is one thing and imparting knowledge effectively is altogether another thing..

November 14, 2020

hot dog not hot dog

November 14, 2020

Thank you !! appreciate the simplicity and clarity in explanation

November 14, 2020

Thank you for this amazing video really appreciated

November 14, 2020

Hi Yufeng,

which book/course would you recommend for a beginner for machine learning?

November 14, 2020

Great way of explaining such a sophisticated topic! Good job!

November 14, 2020

Haha nice. I help teach ML. And I am going to use this to help others understand it. Good recap of supervised learning

November 14, 2020

What is model selection here?

November 14, 2020

3:28 Evaluation is another term testing, isn't

November 14, 2020

woah!!!

November 14, 2020

Hmm good… Hopefully you'll have a course to offer that takes us from a to z of Machine learning.

November 14, 2020

I am here in 2020.

November 14, 2020

The W is upside down

November 14, 2020

This is a very underrated video. keep up the good work!!

November 14, 2020

And don't forget that "Step 1" (buying the booze) is now a tax deductible business expense. You're welcome.

November 14, 2020

Great video's for self learning A.I

November 14, 2020

Amazing

November 14, 2020

what parameters will you consider for detecting flags of certain 2 nations?

November 14, 2020

I need help in creating svm program to detect transmission line faults in matlab for my project…. Can you Help me!