Foundations of PyTorch
Foundations of PyTorch ranks 4th on the list of best online PyTorch courses. This course covers many aspects of developing deep learning models in PyTorch, such as neurons and neural networks, as well as how PyTorch uses differential calculus to train such models and generate dynamic computation graphs in deep learning. In this course, Foundations of PyTorch, you will learn how to use PyTorch's support for dynamic computation graphs and compare it to other popular frameworks like TensorFlow.
First, you'll learn about the inner workings of neurons and neural networks, as well as how activation functions, affine transformations, and layers interact within a deep learning model. Following that, you will learn how such a model is trained, or how the best values of model parameters are estimated. Then you'll see how gradient descent optimization is cleverly used to optimize this process. You will also learn about the various types of differentiation that can be used in this process, as well as how PyTorch implements reverse-mode auto-differentiation using Autograd. You'll also work with PyTorch constructs like Tensors, Variables, and Gradients.
Finally, you will learn how to use PyTorch to create dynamic computation graphs. You'll finish the course by comparing this to the approaches used in TensorFlow, another leading deep learning framework that previously only supported static computation graphs but has recently added support for dynamic computation graphs.
The course includes:
- Getting Started with PyTorch for Machine Learning
- Working with Tensors in PyTorch
- Working with Gradients Using the Autograd Library
- Building Dynamic Computation Graphs
You can take the Foundations of PyTorch certification course on Pluralsight.
Course rating: 4.5 out of 5.0
Duration: 2 h 51 m
Certificate: Certificate on completion
Enroll here: pluralsight.com/courses/foundations-pytorch
