4.19 out of 5
4.19
169 reviews on Udemy

Crash Course in Deep Learning with Google TensorFlow|Python

Google TensorFlow : Learn, Implement Deep Learning & master one of the cornerstone skills of a Data Scientist.
Instructor:
UNP United Network of Professionals
8,013 students enrolled
English [Auto-generated]
TensorFlow installation
Different TensorFlow Environments
Computation graphs
Artificial Neural Networks (ANN)
Convolutional Neural networks (CNN)
Regularization in Neural Networks - Dropout and Max Pooling
Keras & TfLearn
Building a custom Image Classifier on ANY Dataset
Extensive Assignments :Test your Understanding & Periodic Updates on the Subject
Transfer learning and how to use Google inception

This course lays a solid foundation to TensorFlow, a leading machine learning library from Google AI team. You’ll see how TensorFlow can create a range of machine learning models, custom deep neural networks to transfer learning models built by big tech giants. You will learn how to use and reuse tensorflow effectively and apply on industry relevant problems.

Introducting Tensorflow

1
Introduction to Tensorflow

Learning goals of this course are discussed. At the end of this course, you will be able to use tensorflow for practical business applications.

2
Why Tensorflow?

In this lecture, you will learn about some practical applications where Tensorflow can be (is already being) used. Like self face detection in images, driving cars, Amazon Alexa etc..

3
What is tensorflow?

In this lecture, you will learn why Tensorflow is developed by Google Brain team. The key takeaway here is ... Tensorflow is used as interface and implementation for machine learning algorithm.

4
Tensorflow as an Interface

In this lecture, you will learn how Tensorflow supports the interface part, and how Tensorflow supports the implementation part. The key takeaway from this lecture is Tensorflow's capability to scaling a small scale (implemented in your laptop) to an full scale deployment in a seamless way.

5
Tensorflow as an environment

In this lecture, you will learn about the options that are available for Tensorflow 'Language Interface' and Tensorflow 'Execution Environment'

6
Tensors

In this lecture, you will learn about the abstract concept 'tensor'. What is 'tensor' of dimension 0, 1, 2 etc... 

7
Computation Graph

At the end of this lecture, you will be able to:

  • understand the concept of 'computation graph' with very simplified example
  • understand the reason behind the name Tensorflow  
8
Skills Checklist

In this lecture, mandatory and non-mandatory skills for taking this course are discussed. 

Mandatory skills for this course: 

  • some programming experience in at least one high level langauge
  • understanding of basic mathematics and statistics
  • willingness to lean new concept
9
Modules Covered

This lecture list down the key skills that you will develop at the end of this course. 

To summarize, the key skills that you will gain are:

  • Tensorflow - understanding and implementation
  • Artificial Neural Network (ANN)
  • Debugging and monitoring ANN models
  • Transfer Learning
  • Keras, TFLearn
10
Installing Tensorflow

At the end of this lecture, you will be able to:

  • install Tensorflow in your machine
  • verify whether the installation is successful
11
Tensorflow training

In this lecture, you will learn different concepts (related to linear regression) and how these concepts are implemented. In the subsequent lectures, you will learn how these implementations are done using tensorflow.

12
Prepare Data

At the end of this lecture, you will be able to:

  • prepare artificial data
  • normalize data before modelling 
13
Tensor types

At the end of this lecture, you will learn about:

  • Tensorflow types
  • Tensorflow operations
  • computational graph for linear regression
14
Loss and Optimization

At the end of this lecture, you will be able to:

  • setup loss function in Tensorflow
  • User gradient descent optimizer to minimize the loss
15
Running your first tensorflow program

At the end of this lecture, you will be able to:

  • set up a tensorflow session
  • understand how gradient descent works and visualize it in action for linear regression

Building Neural Networks using Tensorflow

1
Back to tensors

At the end of this lecture, you will know the concepts of rank and share of a tensor.

2
Tensorflow data types

In this lecture, you will learn about tensorflow data types. Tensorflow supports standard data types like int, float, complex. You will learn about new data types like qint8, qint16, quint16 etc... These are specific to tensorflow and are called quantized integer data types.

3
CPU vs GPU vs TPU

In this lecture you will learn the differences between CPU, GPU and TPU (tensor processing unit)

4
Tensorflow methods

At the end of this lecture you will learn about the basic methods that are applied to a tensor, like shape, reshape etc..

5
Introduction to Neural Networks

this is an introductory lecture on neural network, its applications, and how neural network works for recognizing images.

6
Neural Network Architecture

At the end of this lecture, you will have a clear understanding of how a single layer neural network works. 

You will understand: ANN architecture, input nodes, weights, activation functions, output of ANN. 

7
Linear Regression example revisited
At the end of this lecture, you will learn:
  • how a linear regression problem can be cast into the neural network architecture
  • the fundamental concept of making a neural network learn by adjusting the weights so that the loss is minimized
8
The Neuron

At the end of this lecture, you will have a clear understanding of:

  • a 'neuron', the fundamental building block of  an artificial neural network
  • weights and activation function of a 'neuron'
9
Neural Network Layers

At the end of this lecture, you will have a clear understanding of:

  • how to build an ANN using simple neurons
  • the concept of layers in an ANN
  • input, hidden, output layers
  • depth of an ANN
10
The MNIST Dataset
  • This lecture is introduction to the first artificial neural network problem in this course. 
  • The MNIST dataset of hand written numbers are used. There is a total of 70,000 images of size 28x28 pixels.
11
Coding MNIST NN Demo

At the end of this lecture, you will be able to:

  • Set up an ANN model using Tesorflow
  • Run tensorflow to estimate parameters
  • Have a clear idea on how weight, bias, activation function for neural network is implemented using tensorflow
12
Summary

This lecture summarizes this section. In this section, the following are covered:

  • Introduction to neural network and basic concepts of a neuron, input layer, output layer, hidden layer, activation function etc..
  • Real example of modeling using MNIST data set. 

Next section is about deep learning. 

Deep Learning using Tensorflow

1
Deepening the network

A brief lecture that starts with the basic questions .... why we need deep neural network, and how to deepen a neural network. Details follow in the next lecture. 

2
Images and Pixels
  • This lecture introduces the following two concepts:
  • neural network are prone to overfit (convolution neural network is a solution, which is discussed later)
  • images are tensors in 3-D (two in space, one in color)


3
How humans recognise images

At the end of this lecture, you will learn:

  • how human recognizes images (with example of a human image)
  • image recognition starts with high level features, and moves to details 

Later you will see the similarity of human being's way of image recognition with deep neural network.

4
Convolutional Neural Networks

At the end of this lecture, you will learn:

  • CNN - convolutional neural networks
  • How CNN works on an image with practical example
  • the concept of feature finding (oblique shapes, horizontal shapes etc..)
  • CNN also overfits, max-pooling is a concept to overcome the overfitting problem. Max pooling also makes the computation more manageable. 
5
ConvNet Architecture

At the end of this lecture, you will understand different layers of deep neural network. 

6
Overfitting and Regularization

At the end of this lecture, you will learn about "overfitting". This is a central concept in machine learning. Regularization is done to mitigate overfitting. Next lecture covers regularization.

7
Max Pooling and ReLU activations

At the end of this lecture, you will understand:

  • the concept of max pooling
  • why sigmoid activation function is not adequate, and reLU is used instead
8
Dropout

At the end of this lecture, you will learn about the concept of "drop out". This is used to regularize the neural network against over fitting.

9
Strides and Zero Padding

At the end of this lecture, you will learn some of the most important concepts of convolutional neural network (CNN). These are:

  • Size of the convolution - the size and shape of the convolution kernel
  • Stride of the convolution - by how much the convolution kernel should move 
  • Padding - how to manage the convolution at the boundaries of the image
10
Coding Deep ConvNets demo

By following this lecture, you will be able to create a deep neural network all by yourself. In particular you will learn:

  • how to construct a neural network layer by layer
  • how to set convolution, activation and max pooling in each layer
  • how to set the loss function
  • how to set the optimizer
11
Debugging Neural Networks

This lecture talks about the necessity of debugging a neural network and introduces a list of tools available for debugging a neural network. In the next lecture the tools are discussed in details. 

12
Visualising NN using Tensorflow

After following this lecture, you will be able to:

  • create logs and summaries of a neural network training process
  • assign name and name scopes to track progress
  • set up a tensorboard to visualize the training progress in real time
  • see accuracy and statistics related to all the weights and biases in real time
13
Tensorboard continued

After following this lecture, you will be able to:

  • go deeper into tensor board
  • check every details of the computational graphs
  • check distribution of weights 
  • check the rate of decrease in loss function and increase in accuracy for every iteration
14
Summary

This lecture summarizes all the topic that is been covered in this Section.

Transfer Learning using Keras and TFLearn

1
Transfer Learning Introduction

At the end of this lecture, you will learn:

  • the concept of transfer learning
  • the advantages of transfer learning
2
Google Inception Model

At the end of this lecture, you will learn the exact steps needed in setting up a transfer learning framework with Google inception.

3
Retraining Google Inception with our own data demo

At the end of this lecture, you will be able to:

  • start implementing your first transfer learning models using Google Inception
  • make changes and update the key arguments of the transfer learning code provided by Google Tensorflow team
  • restructure and prepare data for transfer learning
  • diagnose the learning and testing
4
Predicting new images

At the end of this lecture, you will be able to :

  • use transfer learning for creating your own image classifier
  • debug transfer learning models created using Google inception
5
Transfer Learning Summary

Summary of transfer learning section. In a single sentence ... "adopt pre-trained networks for your applications".

6
Extending Tensorflow

Introduction on how tensorflow can be extended to make programming easy and with less bugs. Two important tools Keras and TFLearn are discussed in the subsequent lectures. 

7
Keras Demo

At the end of this lecture, you will be able to:

  • install and learn Kearas library over Tensorflow
  • develop ANN models by writing only a few lines in Keras
  • use Keras Tensorboard to track progress of the learning phase


8
TFLearn Demo

At the end of this lecture, you will be able to:

  • develop and train neural network models with only few lines of codes in TFLearn
9
Keras vs TFLearn Comparison

At the end of this lecture, you will be able to:

  • understand the differences and similarities between Keras and TFLearn
  • take decision on whether to use Keras or TFLearn for your applications
10
Summary and Conclusion

Summary of the section on: 

  • transfer learning
  • abstraction over tensorflow, - Keras and TFLearn
11
Final Assignment

Tensorflow Extra Resources

1
Tensorflow Interview Questions 1

These make a small part of a comprehensive list of questions popularly asked with Tensorflow.

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!
4.2
4.2 out of 5
169 Ratings

Detailed Rating

Stars 5
66
Stars 4
58
Stars 3
35
Stars 2
5
Stars 1
8
da3d9426cf2cbbc46dc17dd52d09afa9
30-Day Money-Back Guarantee

Includes

4 hours on-demand video
Full lifetime access
Access on mobile and TV
Certificate of Completion