This course aims to teach learners how to use PyTorch for Python 3.5. The learning outcomes include understanding linear models, gradient descent, back-propagation, autograd, linear regression, PyTorch DataLoader, softmax classifier, basic CNN, advanced CNN, wide and deep models, and logistic regression. The course employs lectures to deliver the content. The intended audience for this course is individuals interested in deep learning and neural networks using PyTorch.
Overview
Syllabus
PyTorch Lecture 01: Overview.
PyTorch Lecture 02: Linear Model.
PyTorch Lecture 03: Gradient Descent.
PyTorch Lecture 04: Back-propagation and Autograd.
PyTorch Lecture 05: Linear Regression in the PyTorch way.
PyTorch Lecture 08: PyTorch DataLoader.
PyTorch Lecture 09: Softmax Classifier.
PyTorch Lecture 10: Basic CNN.
PyTorch Lecture 11: Advanced CNN.
PyTorch Lecture 07: Wide and Deep.
PyTorch Lecture 06: Logistic Regression.
PyTorch Lecture 08: PyTorch DataLoader.
PyTorch Lecture 09: Softmax Classifier.
PyTorch in 5 Minutes.
Taught by
iot slottet
