4.53 out of 5
4.53
237 reviews on Udemy

TensorFlow and the Google Cloud ML Engine for Deep Learning

CNNs, RNNs and other neural networks for unsupervised and supervised deep learning
Instructor:
Loony Corn
3,387 students enrolled
English [Auto-generated]
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

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

Introduction

1
You, This Course and Us
2
Source Code and PDFs
3
Datasets for all Labs

Installation

1
Install TensorFlow
2
Install Jupyter Notebook
3
Running on the GCP vs. Running on your local machine
4
Lab: Setting Up A GCP Account
5
Lab: Using The Cloud Shell
6
Datalab ~ Jupyter
7
Lab: Creating And Working On A Datalab Instance

TensorFlow and Machine Learning

1
Introducing Machine Learning
2
Representation Learning
3
Neural Networks Introduced
4
Introducing TensorFlow
5
Running on the GCP vs. Running on your local machine
6
Lab: Simple Math Operations
7
Computation Graph
8
Tensors
9
Lab: Tensors
10
Linear Regression Intro
11
Placeholders and Variables
12
Lab: Placeholders
13
Lab: Variables
14
Lab: Linear Regression with Made-up Data
15
TensorFlow Basics

Working with Images

1
Image Processing
2
Images As Tensors
3
Lab: Reading and Working with Images
4
Lab: Image Transformations
5
Images

K-Nearest-Neighbors with TensorFlow

1
Introducing MNIST
2
K-Nearest Neigbors
3
One-hot Notation and L1 Distance
4
Steps in the K-Nearest-Neighbors Implementation
5
Lab: K-Nearest-Neighbors
6
MNIST with K-Nearest Neighbors

Linear Regression with a Single Neuron

1
Learning Algorithm
2
Individual Neuron
3
Learning Regression
4
Learning XOR
5
XOR Trained

Linear Regression in TensorFlow

1
Lab: Access Data from Yahoo Finance
2
Non TensorFlow Regression
3
Lab: Linear Regression - Setting Up a Baseline
4
Gradient Descent
5
Lab: Linear Regression
6
Lab: Multiple Regression in TensorFlow
7
Linear Regression

Logistic Regression in TensorFlow

1
Logistic Regression Introduced
2
Linear Classification
3
Lab: Logistic Regression - Setting Up a Baseline
4
Logit
5
Softmax
6
Argmax
7
Lab: Logistic Regression
8
Logistic Regression

The Estimator API

1
Estimators
2
Lab: Linear Regression using Estimators
3
Lab: Logistic Regression using Estimators
4
Estimators

Neural Networks and Deep Learning

1
Traditional Machine Learning
2
Deep Learning
3
Operation of a Single Neuron
4
The Activation Function
5
Training a Neural Network: Back Propagation
6
Lab: Automobile Price Prediction - Exploring the Dataset
7
Lab: Automobile Price Prediction - Using TensorFlow for Prediction
8
Hyperparameters
9
Vanishing and Exploding Gradients
10
The Bias-Variance Trade-off
11
Preventing Overfitting
12
Lab: Iris Flower Classification
13
Neural Networks and Deep Learning

Classifiers and Classification

1
Classification as an ML Problem
2
Confusion Matrix: Accuracy, Precision and Recall
3
Decision Thresholds and The Precision-Recall Trade-off
4
F1 Scores and The ROC Curve
5
Classification

Convolutional Neural Networks (CNNs)

1
Mimicking the Visual Cortex
2
Convolution
3
Choice of Kernel Functions
4
Zero Padding and Stride Size
5
CNNs vs DNNs
6
Feature Maps
7
Pooling
8
Lab: Classification of Street View House Numbers - Exploring the Dataset
9
Basic Architecture of a CNN
10
Lab: Classification of Street View House Numbers - Building the Model
You can view and review the lecture materials indefinitely, like an on-demand channel.
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!
4.5
4.5 out of 5
237 Ratings

Detailed Rating

Stars 5
110
Stars 4
86
Stars 3
27
Stars 2
9
Stars 1
5
7b52f0d0b7a25e90143270fb40005af8
30-Day Money-Back Guarantee

Includes

17 hours on-demand video
5 articles
Full lifetime access
Access on mobile and TV
Certificate of Completion