English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 6 Hours | 1.97 GB
eLearning | Skill level: All Levels
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
Welcome! Course introduction
1 Meet your instructors and why you should study machine learning?
2 What does the course cover?
Introduction to neural networks
3 Introduction to neural networks
4 Training the model
5 Types of machine learning
6 The linear model
7 Need Help with Linear Algebra?
8 The linear model. Multiple inputs
9 The linear model. Multiple inputs and multiple outputs
10 Graphical representation
11 The objective function
12 L2-norm loss
13 Cross-entropy loss
14 One parameter gradient descent
15 N-parameter gradient descent
Setting up the working environment
16 Setting up the environment – An introduction – Do not skip, please!
17 Why Python and why Jupyter?
18 Installing Anaconda
19 The Jupyter dashboard – part 1
20 The Jupyter dashboard – part 2
21 Jupyter Shortcuts
22 Installing TensorFlow 2
23 Installing packages – exercise
24 Installing packages – solution
Minimal example – your first machine learning algorithm
25 Minimal example – part 1
26 Minimal example – part 2
27 Minimal example – part 3
28 Minimal example – part 4
29 Minimal example – Exercises
TensorFlow – An introduction
30 TensorFlow outline
31 TensorFlow 2 intro
32 A Note on Coding in TensorFlow
33 Types of file formats in TensorFlow and data handling
34 Model layout – inputs, outputs, targets, weights, biases, optimizer and loss
35 Interpreting the result and extracting the weights and bias
36 Cutomizing your model
37 Minimal example – Exercises
Going deeper: Introduction to deep neural networks
39 What is a deep net?
40 Understanding deep nets in depth
41 Why do we need non-linearities?
42 Activation functions
43 Softmax activation
45 Backpropagation – visual representation
Backpropagation. A peek into the Mathematics of Optimization
46 Backpropagation. A peek into the Mathematics of Optimization
47 Underfitting and overfitting
48 Underfitting and overfitting – classification
49 Training and validation
50 Training, validation, and test
51 N-fold cross validation
52 Early stopping
53 Initialization – Introduction
54 Types of simple initializations
55 Xavier initialization
Gradient descent and learning rates
56 Stochastic gradient descent
57 Gradient descent pitfalls
59 Learning rate schedules
60 Learning rate schedules. A picture
61 Adaptive learning rate schedules
62 Adaptive moment estimation
63 Preprocessing introduction
64 Basic preprocessing
66 Dealing with categorical data
67 One-hot and binary encoding
The MNIST example
68 The dataset
69 How to tackle the MNIST
70 Importing the relevant packages and load the data
71 Preprocess the data – create a validation dataset and scale the data
72 Preprocess the data – scale the test data
73 Preprocess the data – shuffle and batch the data
74 Preprocess the data – shuffle and batch the data
75 Outline the model
76 Select the loss and the optimizer
78 MNIST – exercises
79 MNIST – solutions
80 Testing the model
81 Exploring the dataset and identifying predictors
82 Outlining the business case solution
83 Balancing the dataset
84 Preprocessing the data
85 Preprocessing exercise
86 Load the preprocessed data
87 Load the preprocessed data – Exercise
88 Learning and interpreting the result
89 Setting an early stopping mechanism
90 Setting an early stopping mechanism – Exercise
91 Testing the model
92 Final exercise
Appendix: Linear Algebra Fundamentals
93 What is a Matrix?
94 Scalars and Vectors
95 Linear Algebra and Geometry
96 Scalars, Vectors and Matrices in Python
98 Addition and Subtraction of Matrices
99 Errors when Adding Matrices
100 Transpose of a Matrix
101 Dot Product of Vectors
102 Dot Product of Matrices
103 Why is Linear Algebra Useful?
104 See how much you have learned
105 What’s further out there in the machine and deep learning world
106 An overview of CNNs
107 How DeepMind uses deep learning
108 An overview of RNNs
109 An overview of non-NN approaches
110 Bonus lecture: Next steps