Deep Learning with TensorFlow 2.0 [2020]

Deep Learning with TensorFlow 2.0 [2020]

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 6 Hours | 1.87 GB

Build Deep Learning Algorithms with TensorFlow 2.0, Dive into Neural Networks and Apply Your Skills in a Business Case Data scientists, machine learning engineers, and AI researchers all have their own skillsets. But what is that one special thing they have in common? They are all masters of deep learning. We often hear about AI, or self-driving cars, or the ‘algorithmic magic’ at Google, Facebook, and Amazon. But it is not magic – it is deep learning. And more specifically, it is usually deep neural networks – the one algorithm to rule them all. Cool, that sounds like a really important skill; how do I become a Master of Deep Learning? There are two routes you can take: The unguided route – This route will get you where you want to go, eventually, but expect to get lost a few times. If you are looking at this course you’ve maybe been there. The 365 route – Consider our route as the guided tour. We will take you to all the places you need, using the paths only the most experienced tour guides know about. We have extra knowledge you won’t get from reading those information boards and we give you this knowledge in fun and easy-to-digest methods to make sure it really sticks. Clearly, you can talk the talk, but can you walk the walk? – What exactly will I get out of this course that I can’t get anywhere else? Good question! We know how interesting Deep Learning is and we love it! However, we know that the goal here is career progression, that’s why our course is business focused and gives you real world practice on how to use Deep Learning to optimize business performance. We don’t just scratch the surface either – It’s not called ‘Skin-Deep’ Learning after all. We fully explain the theory from the mathematics behind the algorithms to the state-of-the-art initialization methods, plus so much more. Theory is no good without putting it into practice, is it? That’s why we give you plenty of opportunities to put this theory to use. Implement cutting edge optimizations, get hands on with TensorFlow and even build your very own algorithm and put it through training! Wow, that’s going to look great on your resume! Speaking of resumes, you also get a certificate upon completion which employers can verify that you have successfully finished a prestigious 365 Careers course – and one of our best at that! Now, I can see you’re bragging a little, but I admit you have peaked my interest. What else does your course offer that will make my resume shine? Trust us, after this course you’ll be able to fill your resume with skills and have plenty left over to show off at the interview. Of course, you’ll get fully acquainted with Google’ TensorFlow and NumPy, two tools essential for creating and understanding Deep Learning algorithms. Explore layers, their building blocks and activations – sigmoid, tanh, ReLu, softmax, etc. Understand the backpropagation process, intuitively and mathematically. You’ll be able to spot and prevent overfitting – one of the biggest issues in machine and deep learning Get to know the state-of-the-art initialization methods. Don’t know what initialization is? We explain that, too Learn how to build deep neural networks using real data, implemented by real companies in the real world. TEMPLATES included! Also, I don’t know if we’ve mentioned this, but you will have created your very own Deep Learning Algorithm after only 1 hour of the course. It’s this hands-on experience that will really make your resume stand out What you’ll learn
  • Gain a Strong Understanding of TensorFlow – Google’s Cutting-Edge Deep Learning Framework
  • Build Deep Learning Algorithms from Scratch in Python Using NumPy and TensorFlow
  • Set Yourself Apart with Hands-on Deep and Machine Learning Experience
  • Grasp the Mathematics Behind Deep Learning Algorithms
  • Understand Backpropagation, Stochastic Gradient Descent, Batching, Momentum, and Learning Rate Schedules
  • Know the Ins and Outs of Underfitting, Overfitting, Training, Validation, Testing, Early Stopping, and Initialization
  • Competently Carry Out Pre-Processing, Standardization, Normalization, and One-Hot Encoding
+ Table of Contents

Welcome! Course introduction
1 Meet your instructors and why you should study machine learning
2 What does the course cover
3 Download All Resources and Important FAQ

Introduction to neural networks
4 Introduction to neural networks
5 Training the model
6 Types of machine learning
7 The linear model
8 Need Help with Linear Algebra
9 The linear model. Multiple inputs
10 The linear model. Multiple inputs and multiple outputs
11 Graphical representation
12 The objective function
13 L2-norm loss
14 Cross-entropy loss
15 One parameter gradient descent
16 N-parameter gradient descent

Setting up the working environment
17 Setting up the environment – An introduction – Do not skip, please!
18 Why Python and why Jupyter
19 Installing Anaconda
20 The Jupyter dashboard – part 1
21 The Jupyter dashboard – part 2
22 Jupyter Shortcuts
23 Installing TensorFlow 2
24 Installing packages – exercise
25 Installing packages – solution

Minimal example – your first machine learning algorithm
26 Minimal example – part 1
27 Minimal example – part 2
28 Minimal example – part 3
29 Minimal example – part 4
30 Minimal example – Exercises

TensorFlow – An introduction
31 TensorFlow outline
32 TensorFlow 2 intro
33 A Note on Coding in TensorFlow
34 Types of file formats in TensorFlow and data handling
35 Model layout – inputs, outputs, targets, weights, biases, optimizer and loss
36 Interpreting the result and extracting the weights and bias
37 Cutomizing your model
38 Minimal example with TensorFlow – Exercises

Going deeper Introduction to deep neural networks
39 Layers
40 What is a deep net
41 Understanding deep nets in depth
42 Why do we need non-linearities
43 Activation functions
44 Softmax activation
45 Backpropagation
46 Backpropagation – visual representation

Backpropagation. A peek into the Mathematics of Optimization
47 Backpropagation. A peek into the Mathematics of Optimization

Overfitting
48 Underfitting and overfitting
49 Underfitting and overfitting – classification
50 Training and validation
51 Training, validation, and test
52 N-fold cross validation
53 Early stopping

Initialization
54 Initialization – Introduction
55 Types of simple initializations
56 Xavier initialization

Gradient descent and learning rates
57 Stochastic gradient descent
58 Gradient descent pitfalls
59 Momentum
60 Learning rate schedules
61 Learning rate schedules. A picture
62 Adaptive learning rate schedules
63 Adaptive moment estimation

Preprocessing
64 Preprocessing introduction
65 Basic preprocessing
66 Standardization
67 Dealing with categorical data
68 One-hot and binary encoding

The MNIST example
69 The dataset
70 How to tackle the MNIST
71 Importing the relevant packages and load the data
72 Preprocess the data – create a validation dataset and scale the data
73 Preprocess the data – scale the test data
74 Preprocess the data – shuffle and batch the data
75 Preprocess the data – shuffle and batch the data
76 Outline the model
77 Select the loss and the optimizer
78 Learning
79 MNIST – exercises
80 MNIST – solutions
81 Testing the model

Business case
82 Exploring the dataset and identifying predictors
83 Outlining the business case solution
84 Balancing the dataset
85 Preprocessing the data
86 Preprocessing exercise
87 Load the preprocessed data
88 Load the preprocessed data – Exercise
89 Learning and interpreting the result
90 Setting an early stopping mechanism
91 Setting an early stopping mechanism – Exercise
92 Testing the model
93 Final exercise

Appendix Linear Algebra Fundamentals
94 What is a Matrix
95 Scalars and Vectors
96 Linear Algebra and Geometry
97 Scalars, Vectors and Matrices in Python
98 Tensors
99 Addition and Subtraction of Matrices
100 Errors when Adding Matrices
101 Transpose of a Matrix
102 Dot Product of Vectors
103 Dot Product of Matrices
104 Why is Linear Algebra Useful

Conclusion
105 See how much you have learned
106 What’s further out there in the machine and deep learning world
107 An overview of CNNs
108 How DeepMind uses deep learning
109 An overview of RNNs
110 An overview of non-NN approaches

Bonus lecture
111 Bonus lecture Next steps