The course will teach you how to develop deep learning models using Pytorch. The course will start with Pytorch's tensors and Automatic differentiation package. Then each section will cover different models starting off with fundamentals such as Linear Regression, and logistic/softmax regression. Followed by Feedforward deep neural networks, the role of different activation functions, normalization and dropout layers. Then Convolutional Neural Networks and Transfer learning will be covered. Finally, several other Deep learning methods will be covered.
IBM is the global leader in business transformation through an open hybrid cloud platform and AI, serving clients in more than 170 countries around the world. Today 47 of the Fortune 50 Companies rely on the IBM Cloud to run their business, and IBM Watson enterprise AI is hard at work in more than 30,000 engagements. IBM is also one of the world’s most vital corporate research organizations, with 28 consecutive years of patent leadership. Above all, guided by principles for trust and transparency and support for a more inclusive society, IBM is committed to being a responsible technology innovator and a force for good in the world.
- 5 stars
- 4 stars
- 3 stars
- 2 stars
- 1 star
DEEP NEURAL NETWORKS WITH PYTORCH からの人気レビュー
The material is good. I found the assignments a bit too easy. A bit more challenge would be welcome. I found the artificial voice with the lectures to be distracting. The AI isn't quite good enough.
An extremely good course for anyone starting to build deep learning models. I am very satisfied at the end of this course as i was able to code models easily using pytorch. Definitely recomended!!
This is not a bad course at all. One feedback, however, is making the quizzes longer, and adding difficult questions especially concept-based one in the quiz will be more rewarding and valuable.
The right level of detail so that you can dive in. I wish there had been a week to cover RNNs as well though, in particular the best way to handle variable length sequences for RNNs :)