Assignments and Supplemental Reading Materials

Now that you have built a project and completed the quiz, you are ready to move to the next step: exploring some supplemental reading materials and completing the provided assignments to gain a better understanding of the topics we discussed.

Supplemental reading materials

1. A Survey on Deep Transfer Learning by Chuanqi Tan and others in 2018. This survey focuses on reviewing the research of transfer learning by using a deep neural network and its applications. The authors also defined deep transfer learning and reviewed the recent research based on the techniques used in deep transfer learning.

2. Deep Residual Learning for Image Recognition by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun from Microsoft Research in 2015. As you now know that deeper neural networks are more difficult to train. This paper presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously. This is a good paper and we recommend reading it because the techniques discussed in this paper will help you to succeed in your deep learning career.

3. MobileNets: Efficient Convolutional Neural Networks for Mobile VisionApplications by Andrew G. Howard et al. from Google in 2017. This paper presents a class of efficient models, called MobileNets, for mobile and embedded vision applications. We suggest reading this paper, as you will have an assignment based on MobileNet later in the course.

4. Inception-v4, Inception-ResNet, and the Impact of Residual Connections on Learning by Christian Szegedy et al. from Google in 2016. This paper discusses the Inception networks, which are also one of the pre-trained networks. The authors give clear empirical evidence that training with residual connections significantly accelerates the training of Inception networks.