Lightning AI Studios: Never set up a local environment again →

Log in or create a free Lightning.ai account to track your progress and access additional course materials  

Deep Learning Fundamentals

  • Pages

    • Final certification exam

    Deep Learning Fundamentals > Unit 2 > Unit 2.1
    Course Progress:

    2.1 Introducing PyTorch

    Slides

    References

    What we covered in this video lecture

    In this lecture, we introduce PyTorch. PyTorch is an open-source library for deep learning library that is widely used in both academia and industry. PyTorch originated from the original Torch project, a deep learning framework based on the programming language Lua. In the upcoming videos, we will dive deeper into PyTorch’s tensor data structure before implementing and training deep neural networks.

    Additional resources if you want to learn more

    If you are curious and want to learn more about original Torch library implemented in Lua from a historic perspective, its website and GitHub repository are still online.

    Log in or create a free Lightning.ai account to access:

    • Quizzes
    • Completion badges
    • Progress tracking
    • Additional downloadable content
    • Additional AI education resources
    • Notifications when new units are released
    • Free cloud computing credits

    Quiz: 2.1 Introducing PyTorch

    Which deep learning framework is the most widely used one across research papers according to Papers With Code?

    Correct. As of 2022, PyTorch is currently the most widely used framework by a large margin.

    Incorrect. Since 2019, the use of TensorFlow in research papers has been declining.

    Incorrect. Torch was discontinued a few years ago after PyTorch was released in 2016.

    Incorrect. According to the Papers With Code Trends analysis, JAX is not widely used in research projects.

    We can think of PyTorch as a open source library that consists of and enables 3 core functions. Check all that apply.

    Correct. At its core, PyTorch implements an efficient array/tensor data structure on which all its other functionality is based on.

    Correct. Automatic differentiation, as we will learn later, is one of the corner stones behind training deep neural networks. PyTorch also implements standalone functions for automatic generation.

    Correct. PyTorch offers various abstractions and utilities to fasciliate the implementation and training of deep neural networks.

    Incorrect. PyTorch does not implement tools for creating visualizations (yet).

    Please answer all questions to proceed.
    Watch Video 1

    Unit 2.1

    Videos
    Follow along in a Lightning Studio

    DL Fundamentals 2: Tensors and PyTorch

    Sebastian
    Launch Studio →
    Questions or Feedback?

    Join the Discussion