TensorFlow and the Google Cloud ML Engine for Deep Learning

TensorFlow and the Google Cloud ML Engine for Deep Learning, available at $54.99, has an average rating of 4.55, with 132 lectures, 14 quizzes, based on 306 reviews, and has 4167 subscribers.

You will learn about Build and execute machine learning models on TensorFlow Implement Deep Neural Networks, Convolutional Neural Networks and Recurrent Neural Networks Understand and implement unsupervised learning models such as Clustering and Autoencoders This course is ideal for individuals who are Developers who want to understand and build ML and deep learning models in TensorFlow or Data scientists who want to learn cutting edge TensorFlow technology It is particularly useful for Developers who want to understand and build ML and deep learning models in TensorFlow or Data scientists who want to learn cutting edge TensorFlow technology.

Enroll now: TensorFlow and the Google Cloud ML Engine for Deep Learning

Summary

Title: TensorFlow and the Google Cloud ML Engine for Deep Learning

Price: $54.99

Average Rating: 4.55

Number of Lectures: 132

Number of Quizzes: 14

Number of Published Lectures: 132

Number of Published Quizzes: 14

Number of Curriculum Items: 146

Number of Published Curriculum Objects: 146

Original Price: $89.99

Quality Status: approved

Status: Live

What You Will Learn

Build and execute machine learning models on TensorFlow
Implement Deep Neural Networks, Convolutional Neural Networks and Recurrent Neural Networks
Understand and implement unsupervised learning models such as Clustering and Autoencoders

Who Should Attend

Developers who want to understand and build ML and deep learning models in TensorFlow
Data scientists who want to learn cutting edge TensorFlow technology

Target Audiences

Developers who want to understand and build ML and deep learning models in TensorFlow
Data scientists who want to learn cutting edge TensorFlow technology

TensorFlow is quickly becoming the technology of choice for deep learning, because of how easy TF makes it to build 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 is a comprehensive, from-the-basics course on TensorFlow and building neural networks. It assumes no prior knowledge of Tensorflow, all you need to know is basic Python programming.

What’s covered:

Deep learning basics: What a neuron is; how neural networks connect neurons to ‘learn’ complex functions; how TF makes it easy to build neural network models
Using Deep Learning for the famous ML problems: regression, classification, clustering and autoencoding
CNNs – Convolutional Neural Networks: Kernel functions, feature maps, CNNs v DNNs�
RNNs – Recurrent Neural Networks: LSTMs, Back-propagation through time and dealing with vanishing/exploding gradients
Unsupervised learning techniques – Autoencoding, K-means clustering, PCA as autoencoding�
Working with images
Working with documents and word embeddings
Google Cloud ML Engine: Distributed training and prediction of TF models on the cloud
Working with TensorFlow estimators

Course Curriculum

Chapter 1: Introduction

Lecture 1: You, This Course and Us

Lecture 2: Source Code and PDFs

Lecture 3: Datasets for all Labs

Chapter 2: Installation

Lecture 1: Install TensorFlow

Lecture 2: Install Jupyter Notebook

Lecture 3: Running on the GCP vs. Running on your local machine

Lecture 4: Lab: Setting Up A GCP Account

Lecture 5: Lab: Using The Cloud Shell

Lecture 6: Datalab ~ Jupyter

Lecture 7: Lab: Creating And Working On A Datalab Instance

Chapter 3: TensorFlow and Machine Learning

Lecture 1: Introducing Machine Learning

Lecture 2: Representation Learning

Lecture 3: Neural Networks Introduced

Lecture 4: Introducing TensorFlow

Lecture 5: Running on the GCP vs. Running on your local machine

Lecture 6: Lab: Simple Math Operations

Lecture 7: Computation Graph

Lecture 8: Tensors

Lecture 9: Lab: Tensors

Lecture 10: Linear Regression Intro

Lecture 11: Placeholders and Variables

Lecture 12: Lab: Placeholders

Lecture 13: Lab: Variables

Lecture 14: Lab: Linear Regression with Made-up Data

Chapter 4: Working with Images

Lecture 1: Image Processing

Lecture 2: Images As Tensors

Lecture 3: Lab: Reading and Working with Images

Lecture 4: Lab: Image Transformations

Chapter 5: K-Nearest-Neighbors with TensorFlow

Lecture 1: Introducing MNIST

Lecture 2: K-Nearest Neigbors

Lecture 3: One-hot Notation and L1 Distance

Lecture 4: Steps in the K-Nearest-Neighbors Implementation

Lecture 5: Lab: K-Nearest-Neighbors

Chapter 6: Linear Regression with a Single Neuron

Lecture 1: Learning Algorithm

Lecture 2: Individual Neuron

Lecture 3: Learning Regression

Lecture 4: Learning XOR

Lecture 5: XOR Trained

Chapter 7: Linear Regression in TensorFlow

Lecture 1: Lab: Access Data from Yahoo Finance

Lecture 2: Non TensorFlow Regression

Lecture 3: Lab: Linear Regression – Setting Up a Baseline

Lecture 4: Gradient Descent

Lecture 5: Lab: Linear Regression

Lecture 6: Lab: Multiple Regression in TensorFlow

Chapter 8: Logistic Regression in TensorFlow

Lecture 1: Logistic Regression Introduced

Lecture 2: Linear Classification

Lecture 3: Lab: Logistic Regression – Setting Up a Baseline

Lecture 4: Logit

Lecture 5: Softmax

Lecture 6: Argmax

Lecture 7: Lab: Logistic Regression

Chapter 9: The Estimator API

Lecture 1: Estimators

Lecture 2: Lab: Linear Regression using Estimators

Lecture 3: Lab: Logistic Regression using Estimators

Chapter 10: Neural Networks and Deep Learning

Lecture 1: Traditional Machine Learning

Lecture 2: Deep Learning

Lecture 3: Operation of a Single Neuron

Lecture 4: The Activation Function

Lecture 5: Training a Neural Network: Back Propagation

Lecture 6: Lab: Automobile Price Prediction – Exploring the Dataset

Lecture 7: Lab: Automobile Price Prediction – Using TensorFlow for Prediction

Lecture 8: Hyperparameters

Lecture 9: Vanishing and Exploding Gradients

Lecture 10: The Bias-Variance Trade-off

Lecture 11: Preventing Overfitting

Lecture 12: Lab: Iris Flower Classification

Chapter 11: Classifiers and Classification

Lecture 1: Classification as an ML Problem

Lecture 2: Confusion Matrix: Accuracy, Precision and Recall

Lecture 3: Decision Thresholds and The Precision-Recall Trade-off

Lecture 4: F1 Scores and The ROC Curve

Chapter 12: Convolutional Neural Networks (CNNs)

Lecture 1: Mimicking the Visual Cortex

Lecture 2: Convolution

Lecture 3: Choice of Kernel Functions

Lecture 4: Zero Padding and Stride Size

Lecture 5: CNNs vs DNNs

Lecture 6: Feature Maps

Lecture 7: Pooling

Lecture 8: Lab: Classification of Street View House Numbers – Exploring the Dataset

Lecture 9: Basic Architecture of a CNN

Lecture 10: Lab: Classification of Street View House Numbers – Building the Model

Instructors

Loony Corn
An ex-Google, Stanford and Flipkart team

Rating Distribution

1 stars: 9 votes
2 stars: 11 votes
3 stars: 41 votes
4 stars: 111 votes
5 stars: 134 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu