Launching Into Machine Learning: Machine Learning With TensorFlow On Google Cloud Platform Specialization

102

[editorskit display=”wordcount” before=”Reading Time: ” after=” min”]

The second Machine Learning Course by Google in Machine Learning With TensorFlow on Google Cloud Platform Specialization is Launching Into Machine Learning. Starting with the history of machine learning, in this Launching Into Machine Learning course, there is a discussion on why neural networks perform so well in a variety of data science problems today. Then the course advances by discussing on how to set up a supervised learning problem and find a good solution using gradient descent. This includes creating datasets that allow for normalization where there is discussion about ways to do this, that support experimentation in a repetitive way. This Launching into Machine Learning, Machine Learning Courses by Google can be completed within 1 week in about 5 hours of study.

Course objectives of Launching into Machine Learning:

  • Identify why deep learning is currently popular
  • Using loss functions and performance metrics to optimize and evaluate models
  • Reduce common problems encountered in machine learning
  • Create repetitive and scalable training, evaluation and testing datasets

The skills that you can acquire after completing the Launching into Machine Learning, a specialization of Google Machine Learning Courses are

  • Tensorflow,
  • Bigquery,
  • Machine Learning,
  • Data Cleansing

PLATFORM:COURSERA
PROVIDER:GOOGLE
COST:FREE (AUDIT)
DIFFICULTY:INTERMEDIATE
LANGUAGE:ENGLISH
CERTIFICATE:AVAILABLE
EFFORT:6 HOURS
START DATE:ON GOING
DURATION:1 WEEK
HURRY UP TO ENROLL FOR FREE.

Syllabus – Launching Into Machine Learning

WEEK 1: Introduction

In this second course of Machine Learning With TensorFlow on Google Cloud Platform Specialization, you can get foundational Machine Learning knowledge, so that you can better understand the terminology used in this specialization course. You’ll also learn practical tips and pitfalls from the Machine Learning practitioners from Google and bootstrap your Machine Learning model with code and knowledge.

  • Introduction – (Video) 4 min
  • Intro to Qwiklabs – (Video) 5 min

Practical ML

In this module, you will be introduced to some of the main types of Machine Learning and review the history of Machine Learning leading to the state of the art so that you can accelerate your growth as a Machine Learning practitioner.

  • Introduction – (Video) 1 min
  • Supervised Learning – (Video) 5 min
  • Regression and Classification – (Video) 11 min
  • Short History of ML: Linear Regression – (Video) 7 min
  • Short History of ML: Perceptron – (Video) 5 min
  • Short History of ML: Neural Networks – (Video) 7 min
  • Short History of ML: Decision Trees – (Video) 5 min
  • Short History of ML: Kernel Methods – (Video) 4 min
  • Short History of ML: Random Forests – (Video) 4 min
  • Short History of ML: Modern Neural Networks – (Video) 8 min
  • Module Quiz – (Video) 6 min

Optimization

In this module you can learn how to optimize your Machine Learning models.

  • Introduction – (Video) 42 sec
  • Defining ML Models – (Video) 4 min
  • Introducing the Natality Dataset – (Video) 6 min
  • Introducing Loss Functions – (Video) 6 min
  • Gradient Descent – (Video) 5 min
  • Troubleshooting a Loss Curve – (Video) 2 min
  • ML Model Pitfalls – (Video) 6 min
  • Lab: Introducing the TensorFlow Playground – (Video) 6 min
  • Lab: TensorFlow Playground – Advanced – (Video) 3 min
  • Lab: Practicing with Neural Networks – (Video) 6 min
  • Loss Curve Troubleshooting – (Video) 1 min
  • Performance Metrics – (Video) 3 min
  • Confusion Matrix – (Video) 5 min
  • Module Quiz – (Video) 6 min

Generalization and Sampling

Now is the time to answer a strange question: when is it not right to choose the most accurate ML model? As you may have noticed in the last module on optimization – just because a model has a loss metric of 0 for your training dataset does not necessarily mean it can perform well on new dataset in the real world.

  • Introduction – (Video) 1 min
  • Generalization and ML Models – (Video) 6 min
  • When to Stop Model Training – (Video) 5 min
  • Creating Repeatable Samples in BigQuery – (Video) 6 min
  • Demo: Splitting Datasets in BigQuery – (Video) 8 min
  • Lab Introduction – (Video) 1 min
  • Lab Solution Walk through – (Video) 9 min
  • Lab Introduction – (Video) 2 min
  • Lab Solution Walk through – (Video) 23 min
  • Module Quiz – (Video) 12 min

Summary: Launching Into Machine Learning

  • Module Summary – (Video) 2 min

LEAVE A REPLY

Please enter your comment!
Please enter your name here