Deep Neural Networks in Azure: Transfer Learning and Fine-tuning

Sign in to queue


Deep learning is an emerging field of research, which has applications across multiple fields. We will show how the transfer learning and fine tuning strategy leads to re-usability of the same Deep Convolution Neural Network (DCNN) model in different domains. Attendees will learn about basic deep neural networks, and how to use DNNs in Azure.

In this talk, we propose a method to apply a pre-trained deep convolution neural network (DCNN) on medical images to improve prediction accuracy. We will start with a brief introduction to deep learning and the motivation behind using deep learning models for Medical Images. We will discuss transfer learning and fine-tuning DCNNs in Azure GPU virtual machines and test medical image classification using the fine-tuned DCNN in Azure.

The presenter for this video is Anusua Trivedi, Data Scientist at Microsoft.



Download this episode

The Discussion

Add Your 2 Cents