O'Reilly logo
live online training icon Live Online training

Intermediate Machine Learning with PyTorch

Hands-on analyses of text corpora and images

David Mertz, Ph.D.

PyTorch is one of the premier libraries for programming deep neural networks in Python. There is a great deal of subtlety in the design and implementation of effective neural networks. The course walks the student through creating networks for two popular domain areas: text analysis and image classification. We focus both on the general designs of layers and the specific APIs of PyTorch.

What you'll learn-and how you can apply it

  • Gain an understanding of general NLP (Natural Language Processing) goals.
  • Understand how to apply deep learning techniques to NLP.
  • Utilize and customize pre-trained neural network models.
  • Customize network layers and examine effects of changes.

This training course is for you because...

You are an aspiring or beginning data scientist.
- You have a comfortable intermediate-level knowledge of Python and a very basic familiarity with statistics and linear algebra. - You are a working programmer or student who is motivated to expand your skills to include machine learning with Python. - You have heard about the enormous promise and power of deep neural networks.

Prerequisites

  • A first course in Python and/or working experience as a programmer
  • College-level basic mathematics

Course Set-up

Students should have a system with Jupyter notebooks installed, a recent version of scikit-learn, along with Pandas, NumPy, and matplotlib, and the general scientific Python tool stack. The training materials will be made available as notebooks at a GitHub repository.

Recommended Preparation

These resources are optional, but helpful if you need a refresher on Python, Jupyter Notebooks, or Pandas: - (video) Python Programming Language LiveLessons by David Beazley - (video) Modern Python LiveLessons: Big Ideas and Little Code in Python by Ramond Hettinger - (video) Using Jupyter Notebooks for Data Science Analysis in Python LiveLessons by Jamie Whitacre - (video) Pandas Data Analysis with Python Fundamentals by Daniel Y. Chen

Recommended Follow-up

About your instructor

  • David Mertz was most recently a Senior Trainer and Senior Software Developer for Anaconda, Inc., in which role he created and structured its training program. He was a Director of the Python Software Foundation (PSF) for six years and remains co-chair of its Trademarks Committee and of the PSF Scientific Python Working Group. David worked for nine years with D. E. Shaw Research, some folks who built the world's fastest, highly-specialized (down to the ASICs and network layer) supercomputer for performing molecular dynamics.

    David wrote the widely read columns Charming Python and XML Matters for IBM developerWorks, short books for O'Reilly, and the Addison-Wesley book Text Processing in Python. He has spoken at multiple OSCons, PyCons, and AnacondaCon, and was invited to be a keynote speaker at PyCon-India, PyCon-UK, PyCon-ZA, PyCon Belarus, PyCon Cuba, and PyData SF.

    David is pleased to find Python becoming the default high-level language for most scientific computing projects.

Schedule

The timeframes are only estimates and may vary according to how the class is progressing

Lesson 1: Whirlwind overview of Machine Learning and PyTorch (1 hour)

  • Understand how deep neural networks are different from other ML
  • Understand classification versus regression versus clustering
  • Perform dimensionality reduction
  • Explain feature engineering
  • Types of network layers
  • Tensors and NumPy interfaces
  • Examining Autograd
  • Create a neural network with torch.nn

Lesson 2: Natural Language Processing with AllenNLP (1.5 hours)

  • What is AllenNLP?
  • What is SpaCy?
  • High Level Interfaces to NLP using PyTorch
  • Textual Entailment
  • Named Entity Recognition
  • Semantic Role Labeling
  • Machine Comprehension

Lesson 3: Enhancing an Image Classifier (1.5 hour)

  • Starting with torchvision.models
  • Retraining pretrained models
  • Modifying Network Layers
  • Understanding Effects of Network Structure