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 2.7
    Course Progress:

    2.7 Seeing Predictive Models as Computation Graphs

    Slides

    What we covered in this video lecture

    In this lecture, we created a computation graph visualization representing the perceptron model. Creating a computation graph is a great way to make a complex model more accessible. This also allows us to view the prediction (forward path) and parameter learning (backward path) in a step-wise fashion. In future units, we will use computation graphs to make complicated mathematical concepts of learning algorithms more intuitive.

    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: 2.7 Seeing Predictive Models as Computation Graphs

    Suppose you wrote the following code to convert the temperature from Celsius to Fahrenheit: fahrenheit = (celsius * 9/5) +32). Note that this function does not have any learnable parameters. Nonetheless, we want to create a visual representation, can we create a computation graph?

    Correct. A function or computation does not need to have learnable parameters to represent it as a graph.

    Incorrect. A function or computation does not need to have learnable parameters to represent it as a graph.

    Please answer all questions to proceed.
    Watch Video 1

    Unit 2.7

    Videos
    Follow along in a Lightning Studio

    DL Fundamentals 2: Tensors and PyTorch

    Sebastian
    Launch Studio →
    Questions or Feedback?

    Join the Discussion