English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 84 lectures (8h 38m) | 4.26 GB

Your Complete Guide to Implementing PyTorch, Keras, Tensorflow Algorithms: Neural Networks and Deep Learning in Python

THIS IS A COMPLETE NEURAL NETWORKS & DEEP LEARNING TRAINING WITH PYTORCH, H2O, KERAS & TENSORFLOW IN PYTHON!

It is a full 5-Hour+ Deep Learning Boot Camp that will help you learn basic machine learning, neural networks and deep learning using one of the most important Python Deep Learning frameworks- PyTorch, H2O, Keras & Tensorflow.

HERE IS WHY YOU SHOULD ENROLL IN THIS COURSE:

This course is your complete guide to practical machine & deep learning using the PyTorch, H2O, Keras and Tensorflow framework in Python.

This means, this course covers the important aspects of these architectures and if you take this course, you can do away with taking other courses or buying books on the different Python-based- deep learning architectures.

In this age of big data, companies across the globe use Python to sift through the avalanche of information at their disposal and advent of frameworks such as PyTorch, Keras, H2o, Tensorflow is revolutionizing Deep Learning…

By gaining proficiency in PyTorch, H2O, Keras and Tensorflow, you can give your company a competitive edge and boost your career to the next level.

THIS IS MY PROMISE TO YOU: COMPLETE THIS ONE COURSE & BECOME A PRO IN PRACTICAL PYTHON BASED DATA SCIENCE!

But first things first. My name is Minerva Singh and I am an Oxford University MPhil (Geography and Environment), graduate. I recently finished a PhD at Cambridge University (Tropical Ecology and Conservation).

I have several years of experience in analyzing real-life data from different sources using data science-related techniques and producing publications for international peer-reviewed journals.

Over the course of my research, I realized almost all the Python data science courses and books out there do not account for the multidimensional nature of the topic and use data science interchangeably with machine learning.

This gives students an incomplete knowledge of the subject. My course, on the other hand, will give you a robust grounding in all aspects of data science within the PyTorch, H2O, Tensorflow and Keras framework.

Unlike other Python courses and books, you will actually learn to use PyTorch, H20, Tensorflow and Keras on real data! Most of the other resources I encountered showed how to use PyTorch on in-built datasets which have limited use.

DISCOVER 7 COMPLETE SECTIONS ADDRESSING EVERY ASPECT OF IMPORTANT DEEP LEARNING FRAMEWORKS:

- A full introduction to Python Data Science and powerful Python driven framework for data science, Anaconda
- Getting started with Jupyter notebooks for implementing data science techniques in Python
- A comprehensive presentation about PyTorch, H2o, Tensorflow and Keras installation and a brief introduction to the other Python data science packages
- A brief introduction to the working of important data science packages such as Pandas and Numpy
- The basics of the PyTorch, H2o, Tensorflow and Keras syntax
- The basics of working with imagery data in Python
- The theory behind neural network concepts such as artificial neural networks, deep neural networks and convolutional neural networks (CNN)
- You’ll even discover how to create artificial neural networks and deep learning structures with PyTorch, Keras and Tensorflow (on real data)

BUT, WAIT! THIS ISN’T JUST ANY OTHER DATA SCIENCE COURSE:

You’ll start by absorbing the most valuable PyTorch, Tensorflow and Keras basics and techniques.

I use easy-to-understand, hands-on methods to simplify and address even the most difficult concepts.

My course will help you implement the methods using real data obtained from different sources. Many courses use made-up data that does not empower students to implement Python-based data science in real -life.

After taking this course, you’ll easily use packages like Numpy, Pandas, and PIL to work with real data in Python along with gaining fluency in the most important of deep learning architectures. I will even introduce you to deep learning models such as Convolution Neural network (CNN) !!

The underlying motivation for the course is to ensure you can apply Python-based data science on real data into practice today, start analyzing data for your own projects whatever your skill level, and impress your potential employers with actual examples of your data science abilities.

It is a practical, hands-on course, i.e. we will spend some time dealing with some of the theoretical concepts related to data science. However, the majority of the course will focus on implementing different techniques on real data and interpret the results. Some of the problems we will solve include identifying credit card fraud and classifying the images of different fruits.

After each video, you will learn a new concept or technique which you may apply to your own projects!

What you’ll learn

- Harness The Power Of Anaconda/iPython For Practical Data Science (Including AI Applications)
- Learn How To Install & Use Important Deep Learning Packages Within Anaconda (Including Keras, H20, Tensorflow and PyTorch)
- Implement Statistical & Machine Learning Techniques With Tensorflow
- Implement Neural Network Modelling With Deep learning Packages Including Keras

## Table of Contents

**Introduction to the Course**

1 Introduction

2 Data and Scripts

3 Why Artificial Intelligence and Deep Learning

4 Get Started With the Python Data Science Environment Anaconda

5 Anaconda for Mac Users

6 The iPython Environment

**Introduction to Common Python Data Science Packages**

7 Python Packages for Data Science

8 NUMPY Introduction to Numpy

9 Create Numpy Arrays

10 Numpy Operations

11 Numpy for Basic Vector Arithmetric

12 Numpy for Basic Matrix Arithmetic

13 PANDAS What are Pandas

14 Read in CSV data

15 Read in Excel data

16 Basic Data Exploration With Pandas

**Theoretical Foundations of Artificial Neural Networks (ANN) & Deep Learning (DL)**

17 Theory Behind ANN (Artificial Neural Network) and DNN (Deep Neural Networks)

18 Perceptrons for Binary Classification

19 ANN For Binary Classification

20 What Are Activation Functions Theory

21 More on Backpropagation

22 Multi-label classification with MLP

23 Regression with MLP

24 Other Accuracy Metrics

**Introduction to Artificial Intelligence Python Packages PyTorch**

25 Start With H20

26 Welcome to Tensorflow

27 Install Tensorflow

28 What are Tensors

29 Introduction to Computational Graphs

30 Common Tensorflow Operations

31 Welcome to Keras

32 Keras Installation on Windows 10

33 Keras Installation on Mac OS

34 Written Instructions

35 Why PyTorch

36 Install PyTorch

37 PyTorch Basics What Is a Tensor

38 Explore PyTorch Tensors and Numpy Arrays

39 Some Basic PyTorch Tensor Operations

**Implementing ANN With Python**

40 Implement Multi Layer Perceptron (MLP) with Tensorflow

41 Multi Layer Perceptron (MLP) With Keras

42 Keras MLP For Binary Classification

43 Keras MLP for Multiclass Classification

44 Keras MLP for Regression

45 Implement ANN With H2O

46 PyTorch ANN Syntax

47 Setting Up ANN Analysis With PyTorch

48 How the Different Components of Neural Networks Come Together PyTorch Example

**Implementing DNNs With Python**

49 Deep Neural Network (DNN) Classifier With Tensorflow

50 Deep Neural Network (DNN) Classifier With Mixed Predictors

51 Deep Neural Network (DNN) Regression With Tensorflow

52 Wide & Deep Learning (Tensorflow)

53 DNN Classifier With Keras

54 DNN Classifier With Keras-Example 2

55 DNN Classifier With H2O

56 DNN Analysis with PyTorch

57 More DNNs

58 DNNs For Identifying Credit Card Fraud

**Unsupervised Learning with Deep Learning**

59 What is Unsupervised Learning

60 Autoencoders for Unsupervised Classification

61 Autoencoders in Tensorflow (Binary Class Problem)

62 Autoencoders in Tensorflow (Multiple Classes)

63 Autoencoders in Keras (Sparsity Constraints)

64 Autoencoders in Keras (Simple)

65 Deep Autoencoder With Keras

66 Denoise

**Working With Imagery Data and Computer Vision**

67 What Are Images

68 Read in Images in Python

69 Some Basic Image Conversions

70 Basic Image Resizing

**Convolution Neural Networks (CNN)**

71 What are CNNs

72 Implement a CNN for Multi-Class Supervised Classification

73 What Are Activation Functions

74 More on CNN

75 Pre-Requisite For Working With Imagery Data

76 CNN on Image Data-Part 1

77 CNN on Image Data-Part 2

78 Implement CNN With TFLearn

79 CNN Workflow for Keras

80 CNN With Keras

81 CNN on Image Data with Keras-Part 2

**Transfer Learning**

82 Theory Behind Transer Learning

83 Implement an InceptionV3 model on Real Images

**Miscellaneous Lectures**

84 Github Intro

Resolve the captcha to access the links!