Deep Learning with PyTorch - Zero to GANs

Learn PyTorch from the very basics to advanced models like Generative Adverserial Networks and Image Captioning
Rating: 4.4 out of 5 (177 ratings)
13,235 students
English [Auto]
Deep Learning with PyTorch - Zero to GANs
Rating: 4.4 out of 5 (177 ratings)
13,235 students
A coding-focused introduction to Deep Learning using PyTorch, starting from the very basics and going all the way up to advanced topics like Generative Adverserial Networks


  • Basic knowledge of Python
  • Basic linear algebra (vectors, matrices etc.)


"PyTorch: Zero to GANs" is an online course and series of tutorials on building deep learning models with PyTorch, an open source neural networks library. Here are the concepts covered in this course:

  1. PyTorch Basics: Tensors & Gradients

  2. Linear Regression & Gradient Descent

  3. Classification using Logistic Regression

  4. Feedforward Neural Networks & Training on GPUs (this post)

  5. Coming soon.. (CNNs, RNNs, transfer learning, GANs etc.)

This course will be updated on a weekly basis with new material.

Who this course is for:

  • Students and developers curious about data science
  • Data scientists and machine learning engineers curious about PyTorch

Course content

3 sections • 13 lectures • 1h 33m total length
  • Introduction to Machine Learning
  • System Setup and Jupyter notebook for "PyTorch Basics"
  • PyTorch Basics: Tensors and Gradients


Software Consultant & Entrepreneur
Aakash N S
  • 4.5 Instructor Rating
  • 229 Reviews
  • 28,783 Students
  • 2 Courses

I'm a Software Consultant and Entrepreneur. I've worked extensively on dozens of products and technologies with teams around the world, including Silicon Valley, Japan, Germany, Israel and India. As an entrepreneur I've launched multiple products that have gone on to acquire 100s of thousands of users. Teaching is my passion, and I often conduct workshops for emerging technologies I'm interested in. I also like to write blogs and develop open source software in my free time.