by Goku Mohandas, Alfredo Canziani | Released May 2018 | ISBN: 9781491989951

This video teaches you how to build a powerful image classifier in just minutes using convolutional neural networks and PyTorch. It reviews the fundamental concepts of convolution and image analysis; shows you how to create a simple convolutional neural network (CNN) with PyTorch; and demonstrates how using transfer learning with a deep CNN to train on image datasets can generate state-of-the-art performance. The course is designed for the software engineer looking to get started with deep learning and for the AI researcher with TensorFlow or Theano experience who wants a smooth transition into PyTorch. Prerequisites include an understanding of algebra, basic calculus, and basic Python skills. Learners should download and install PyTorch before starting class. Learn how to build a powerful image classifier in minutes using PyTorchExplore the basics of convolution and how to apply them to image recognition tasksLearn how to do transfer learning in conjunction with powerful pretrained modelsGain experience using powerful deep learning models for image recognition tasksGoku Mohandas is an AI researcher in Silicon Valley. Goku's experience includes working in the intersection of AI and biotechnology for the Johns Hopkins University Applied Physics Laboratory. He holds an MS in Machine Learning from the Georgia Institute of Technology. Alfredo Canziani has a PhD in Artificial Intelligence from Purdue University, where he serves as a Principal Lecturer in AI and deep learning. Both men are deeply committed to the democratization of AI with a focus on interpretability and transparency. Show and hide more Publisher Resources Download Example Code

1. Course Introduction 00:00:43
2. The Curse of Dimensionality with Traditional Feed Forward Networks 00:07:16
3. Exploiting Locality and Stationarity of Data with Convolutions 00:10:01
4. CNNs for Image Processing 00:07:34
5. Simple CNN for MNIST classification using PyTorch 00:10:47
6. Popular CNN Architectures for Image Recognition 00:03:42
7. Using Popular CNNs in PyTorch 00:04:40
8. CNNs for Document Classification using PyTorch 00:08:30
9. Conclusion 00:01:18
Show and hide more