Google Cloud Machine Learning with TensorFlow

Google Cloud Machine Learning with TensorFlow

Train and predict your models using the Google Cloud ML Engine

Bestseller
Created By: Tobias Zwingmann
16.05 9.62

About This Course

TensorFlow has become the first choice for deep learning tasks because of the way it facilitates building powerful and sophisticated neural networks. The Google Cloud Platform is a great place to run TF models at scale, and perform distributed training and prediction.
This course shows you how to use Google Cloud to train TensorFlow models and use them to predict results for multiple users. You will learn to efficiently train neural networks using large datasets and to serve your training models.
With this video course, you will use the power of Google's Cloud Platform to train deep neural networks faster. This course supplies various examples of training in Google Cloud AI Platform. You will also learn to run predictions for your model using the cloud. You will explore topics such as cloud infrastructures, distributed training, serverless technologies, model serving, and more.
By the end of the course, you will be expert at training and serving neural models, and beyond.

The code files and related files are placed on GitHub at https://github.com/PacktPublishing/Google-Cloud-Machine-Learning-with-TensorFlow

Other Information

  • Certificate will provided in this course on Completion
  • Full lifetime access
  • Available on Mobile & Laptop

What Students Will Learn In Your Course?

  • Get access to powerful computers with GPUs organized in clusters to optimize your performance
  • Train bigger models faster using the Google Cloud infrastructure
  • Explore machine types and learn how to configure clusters to solve problems
  • Train deep learning models using the Google Cloud AI Platform
  • Run classical machine learning algorithms with TensorFlow
  • Run your trained models to get predictions using the AI Platform API

Are There Any Course Requirements Or Prerequisites?

Basic knowledge of Data Science is required.

Who Are Your Target Students?

This course targets data scientists, people starting their journey in the ML/DL domain, and anyone keen to start training deep neural networks using cloud infrastructures. Familiarity with ML concepts will be advantageous.

Course Content

  • 40 lectures
  • 04:02:42
  • The Course Overview
    00:06:49
  • Introduction to the Google Cloud Platform
    00:07:07
  • Getting a GCP Account
    00:02:16
  • Walking Through the GCP Console and Google Cloud SDK
    00:07:43
  • Google Compute and Google Storage
    00:05:49
  • AI Platform Overview
    00:02:55
  • Example Workflow with AI Platform Notebooks
    00:11:54
  • What Is TensorFlow and What are TensorFlow APIs?
    00:07:45
  • Lab: Programming in TensorFlow
    00:08:53
  • Using TensorBoard
    00:03:44
  • Overview of Machine Learning
    00:06:27
  • Lab: Linear Regression on TensorFlow
    00:10:39
  • Logistic Regression
    00:04:31
  • Lab: Logistic Regression on TensorFlow
    00:05:35
  • K-Nearest Neighbor (KNN)
    00:03:57
  • Lab: KNN on TensorFlow
    00:06:44
  • Lab: Project Setup
    00:02:00
  • Lab: Staging Data and Preprocessing
    00:05:14
  • Model Training Using Keras API
    00:02:02
  • Lab: Testing Model Predictions
    00:03:50
  • Lab: Exporting the Model for Production
    00:04:29
  • Project Setup
    00:03:56
  • Lab: Staging Data and Preprocessing
    00:10:29
  • Defining the Model
    00:03:14
  • Lab: Defining the Distribution Strategy
    00:04:02
  • Lab: Distributed Training
    00:03:29
  • Lab: Monitor Learning Process in TensorBoard
    00:06:31
  • Overview: Methods for Serving TensorFlow Models on GCP
    00:15:07
  • Lab: Setting Up TensorFlow Serving
    00:01:47
  • Inference Using TensorFlow Serving
    00:07:02
  • Lab: Deploying Models to AI Platform
    00:05:49
  • Lab: Inference Using AI Platform
    00:05:27
  • Lab: Setting Up Cloud Functions for TensorFlow
    00:07:34
  • Lab: Inference Using Cloud Functions
    00:03:57
  • Introduction to Neural Network
    00:06:25
  • Feedforward and Activation Function
    00:03:37
  • Gradient Descent
    00:06:43
  • Backpropagation
    00:05:19
  • One Hot Encoding, Softmax, and Cross-Entropy
    00:07:30
  • Lab: Building a Simple Neural Network on TensorFlow
    00:14:21
Image

Packt Publication

  • 4.4 (6)
  • 7 Reviews
  • 6 Students
  • 935 Courses