Deep Neural Networks with PyTorch
The course will show you how to use Pytorch to create deep learning models. The lecture will begin with the use of Pytorch's tensors and the Automatic Differentiation package. Then, in each session, you'll learn about different models, starting with the basics like linear regression and logistic/softmax regression. The role of different activation functions, normalization, and dropout layers are followed by Feedforward deep neural networks.
Then there will be a discussion of Convolutional Neural Networks and Transfer Learning. Finally, a variety of different Deep Learning techniques will be discussed. Learners will be able to describe and apply their understanding of Deep Neural Networks and associated machine learning methods after finishing this course. They will also be able to use Python libraries such as PyTorch to create Deep Neural Networks.
After completing this course, you will be able to comprehend the theory and understanding underlying Deep Neural Networks, Residual Nets, and Convolutional Neural Networks (CNNs); and build a deep learning model using Keras and Tensorflow 2.0 as a backend.
This course offers:
- Flexible deadlines: Reset deadlines in accordance to your schedule.
- Certificate: Earn a Certificate upon completion• 100% online
- Intermediate Level
- Approx. 31 hours to complete
- Subtitles: Arabic, French, Portuguese (European), Italian, Vietnamese, German, Russian, English, Spanish
Coursera Rating: 4.4/5
Enroll here: https://www.coursera.org/learn/deep-neural-networks-with-pytorch#about
