The 7 steps of machine learning




[ad_1]

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

Learn more through our hands-on labs → https://goo.gle/32sVCBk

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

#AIAdventures

Source


[ad_2]

Comment List

  • Google Cloud Platform
    November 14, 2020

    Excellent!

  • Google Cloud Platform
    November 14, 2020

    Spreadsheets, makes information; presentable.

  • Google Cloud Platform
    November 14, 2020

    People get this stuff wrong, trust me!

  • Google Cloud Platform
    November 14, 2020

    Useful. Thank you!

  • Google Cloud Platform
    November 14, 2020

    Good resource!!! thank you

  • Google Cloud Platform
    November 14, 2020

    4

  • Google Cloud Platform
    November 14, 2020

    Excellent overview and great example.

  • Google Cloud Platform
    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

  • Google Cloud Platform
    November 14, 2020

    Awesome presentation! Clean, short and sweet.

  • Google Cloud Platform
    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.

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    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.

  • Google Cloud Platform
    November 14, 2020

    Data is new currency

  • Google Cloud Platform
    November 14, 2020

    Simply, the best !

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

    Best book for ai and machine learning

  • Google Cloud Platform
    November 14, 2020

    Wine…

  • Google Cloud Platform
    November 14, 2020

    kill the background music!

  • Google Cloud Platform
    November 14, 2020

    This is simple and straightforward. Thanks

  • Google Cloud Platform
    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?"

  • Google Cloud Platform
    November 14, 2020

    Thank you

  • Google Cloud Platform
    November 14, 2020

    Why all examples are alcohol based? !

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

    hot dog not hot dog

  • Google Cloud Platform
    November 14, 2020

    Thank you !! appreciate the simplicity and clarity in explanation

  • Google Cloud Platform
    November 14, 2020

    Thank you for this amazing video really appreciated

  • Google Cloud Platform
    November 14, 2020

    Hi Yufeng,

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

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    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

  • Google Cloud Platform
    November 14, 2020

    What is model selection here?

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

    woah!!!

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

    I am here in 2020.

  • Google Cloud Platform
    November 14, 2020

    The W is upside down

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

    Great video's for self learning A.I

  • Google Cloud Platform
    November 14, 2020

    Amazing

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

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

  • Google Cloud Platform
    November 14, 2020

    Best company in the world ^_^….

  • Google Cloud Platform
    November 14, 2020

    Great video! I my opinion data preparation is the one of the most important thing in Machine Learning.

  • Google Cloud Platform
    November 14, 2020

    This is the most clearly entry point for Learning Machine I ever seen..

Write a comment