English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 11 Hours | 3.59 GB
RNN-Recurrent Neural Networks, Theory & Practice in Python-Learning Automatic Book Writer an Stock Price Prediction
Recurrent Neural Networks (RNNs), a class of neural networks, are essential in processing sequences such as sensor measurements, daily stock prices, etc. In fact, most of the sequence modelling problems on images and videos are still hard to solve without Recurrent Neural Networks. Further, RNNs are also considered to be the general form of deep learning architecture. Hence, the understanding of RNNs is crucial in all the fields of Data Science. This course addresses all these concerns and empowers you to take your career to the next level with a masterful grip on the theoretical concepts and practical implementations of RNNs in Data Science.
Why Should You Enroll in This Course?
The course ‘Recurrent Neural Networks, Theory and Practice in Python’ is crafted to help you understand not only how to build RNNs but also how to train them. This straightforward learning by doing a course will help you in mastering the concepts and methodology with regards to Python.
The two mini-projects Automatic Book Writer and Stock Price Prediction, are designed to improve your understanding of RNNs and add more skills to your data science toolbox. Also, this course will enable you to immediately apply the skills you acquire to your own projects. This course is:
- Easy to understand.
- Expressive and self-explanatory.
- To the point.
- Practical with live coding.
- Thorough, covering the most advanced and recently discovered RNN models by renowned data scientists.
How Is This Course Different?
This is a practical course that encourages you to explore and experience the real-world applications of RNNs. The course starts with the basics of how RNNs work and then goes far deep gradually. So, if your ambition is to become a Python developer, this course is indispensable.
You are assigned Home Work/ tasks/ activities at the end of the subtopics in each module. The reason for this is to make your learning easier and also to assess and further build your learning based on the concepts and methods you have learned previously. Most of these activities are coding based, preparing you for implementing the concepts you learn at your workplace.
With a core understanding of RNNs, you can sharpen your deep learning skills and ensure emerging career growth. Data Science, as a career path, is certainly rewarding. You not only get the opportunity to solve some of the most interesting problems, but you are also assured of a handsome salary package.
This course presents you with a cost-effective option to learn the concepts and methodologies of RNNs with Data Science. Our tutorials are subdivided into a series of short, in-depth HD videos along with detailed code notebooks.
What you’ll learn
- The importance of Recurrent Neural Networks (RNNs) in Data Science.
- The important concepts from the absolute beginning with a comprehensive unfolding with examples in Python.
- The reasons to shift from classical sequence models to RNNs.
- Practical explanation and live coding with Python.
- An overview of concepts of Deep Learning Theory.
- Deep details of RNNs with examples and derivations.
- TensorFlow (Deep learning framework by Google).
- The use and applications of state-of-the-art RNNs (with implementations in state-of-the-art framework TensorFlow) that are much more recent and advanced in terms of accuracy and efficiency.
- Building your own applications for automatic text generation as well as for stock price prediction.
- And much more…
Table of Contents
Introduction to Course
1 Introduction to Instructor and Aisciences
2 Focus of the Course
3 Request for Your Honest Review
4 Link to Github to get the Python Notebooks
Applications of RNN (Motivation)
5 Human Activity Recognition
6 Image Captioning
7 Machine Translation
8 Speech Recognition
9 Stock Price Predictions
10 When to Model RNN
11 Activity
DNN Overview
12 Introduction to Deep Learning Module
13 Neuron and Perceptron
14 DNN Architecture
15 FeedForward FullyConnected MLP
16 Calculating Number of Weights of DNN
17 Number of Nuerons vs Number of Layers
18 Discriminative vs Generative Learning
19 Universal Approximation Therorem
20 Why Depth
21 Decision Boundary in DNN
22 Bias Term
23 Activation Function
24 DNN Training Parameters
25 Gradient Descent
26 Backpropagation
27 Training DNN Animantion
28 Weigth Initialization
29 Batch miniBatch Stocastic
30 Batch Normalization
31 Rprop Momentum
32 Convergence Animation
33 DropOut EarlyStopping Hyperparameters
RNN Architecture
34 Introduction to Module
35 Fixed Length Memory Model
36 Infinite Memory Architecture
37 Weight Sharing
38 Notations
39 ManyToMany Model
40 OneToMany Model
41 ManyToOne Model
42 Activity Many to One
43 ManyToMany Different Sizes Model
44 Activity Many to Many Nmt
45 Models Summary
46 Deep RNNs
Gradient Decsent in RNN
47 Introduction to Gradient Descent Module
48 Example Setup
49 Equations
50 Loss Function
51 Why Gradients
52 Chain Rule
53 Chain Rule in Action
54 BackPropagation Through Time
55 Activity
Vanishing Gradients in RNN
56 Introduction to Better RNNs Module
57 Introduction Vanishing Gradients in RNN
58 GRU
59 GRU Optional
60 LSTM
61 LSTM Optional
62 Bidirectional RNN
63 Attention Model
64 Attention Model Optional
TensorFlow
65 Introduction to TensorFlow
66 TensorFlow Text Classification Example using RNN
Project I Book Writer
67 Introduction
68 Data Mapping
69 Modling RNN Architecture
70 Modling RNN Model in TensorFlow
71 Modling RNN Model Training
72 Modling RNN Model Text Generation
73 Activity
Project II Stock Price Prediction
74 Problem Statement
75 Data Set
76 Data Prepration
77 RNN Model Training and Evaluation
78 Activity
Further Readings and Resourses
79 Further Readings and Resourses 1
Bonus Lecture
80 THANK YOU Bonus Video
Resolve the captcha to access the links!