Applied Deep Learning with PyTorch

Course Description Overview

Course Number:
035458
Course Length:
2 days
Course Description Overview:
Starting with the basics of deep learning and their various applications, Applied Deep Learning with PyTorch shows you how to solve trending tasks, such as image classification and natural language processing by understanding the different architectures of the neural networks.

Machine learning is rapidly becoming the most preferred way of solving data problems, thanks to the huge variety of mathematical algorithms that find patterns, which are otherwise invisible to us.


Applied Deep Learning with PyTorch takes your understanding of deep learning, its algorithms, and its applications to a higher level. The course begins by helping you browse through the basics of deep learning and PyTorch. Once you are well versed with the PyTorch syntax and capable of building a single-layer neural network, you will gradually learn to tackle more complex data problems by configuring and training a convolutional neural network (CNN) to perform image classification. As you progress through the chapters, you’ll discover how you can solve an NLP problem by implementing a recurrent neural network (RNN).


By the end of this course, you’ll be able to apply the skills and confidence you've gathered along your learning process to use PyTorch for building deep learning solutions that can solve your business data problems.


Course Objectives:

After completing this course, you will be able to:

  • Detect a variety of data problems to which you can apply deep learning solutions
  • Learn the PyTorch syntax and build a single-layer neural network with it
  • Build a deep neural network to solve a classification problem
  • Develop a style transfer model
  • Implement data augmentation and retrain your model
  • Build a system for text processing using a recurrent neural network
Target Student:
Applied Deep Learning with PyTorch takes a practical and hands-on approach, where every lesson has a practical example that is demonstrated end-to-end, from data acquisition to result interpretation. Considering the complexity of the concepts at hand, the lessons include several graphical representations to facilitate learning.
Applied Deep Learning with PyTorch is designed for data scientists, data analysts, and developers who want to work with data using deep learning techniques. Anyone looking to explore and implement advanced algorithms with PyTorch will also find this course useful. Some working knowledge of Python and familiarity with the basics of machine learning are a must. However, knowledge of NumPy and pandas will be beneficial, but not essential.
Prerequisites:
-
Course-specific Technical Requirements Software:
  • · OS: Windows 7 SP1 64-bit, Windows 8.1 64-bit or Windows 10 64-bit, Ubuntu Linux, or the latest version of OS X
  • · Browser: Google Chrome/Mozilla Firefox Latest Version
  • · Notepad++/Sublime Text as IDE (Optional, as you can practice everything using Jupyter notebook on your browser)
  • · Python 3.4+ (latest is Python 3.7) installed (from https://python.org)
  • · Python libraries as needed (Jupyter, Numpy, Pandas, Matplotlib, BeautifulSoup4, and so on)
Course-specific Technical Requirements Hardware:

For the optimal student experience, we recommend the following hardware configuration:

  • Processor: i5 or equivalent
  • Memory: 4 GB RAM
  • Hard disk: 35 GB available space
Certification reference (where applicable)
-
Course Content:

Lesson 1: Introduction to Deep Learning and PyTorch

  • Understanding Deep Learning
  • PyTorch Introduction


Lesson 2: Building Blocks of Neural Networks

  • Introduction to Neural Networks
  • Data Preparation
  • Building a Neural Network


Lesson 3: A Classification Problem Using DNN

  • Problem Definition
  • Dealing with an Underfitted or Overfitted Model
  • Deploying Your Model


Lesson 4: Convolutional Neural Networks

  • Building a CNN
  • Data Augmentation
  • Batch Normalization


Lesson 5: Style Transfer

  • Style transfer
  • Implementation of Style Transfer Using the VGG-19 Network Architecture

 

Lesson 6: Analyzing the Sequence of Data with RNNs

  • Recurrent Neural Networks
  • Long Short-Term Memory Networks (LSTMs)
  • LSTM Networks in PyTorch
  • Natural Language Processing (NLP)
  • Sentiment Analysis in PyTorch
Registration
Register Now