March 15th lecture questions
Please respond to these questions by Wednesday noon at the latest. We expect short answers. There is no correct answer and we are not expecting you to spend a long time on this; the goal is to check that you've read the articles and to raise discussion points that we will go over in class.
Please enter your MIT ID *
Your answer
[Bejnordi et al. 2017] The authors use three neural networks in their pipeline. What are they and what is their use? *
Your answer
[Bejnordi et al. 2017] Even though the features extracted from CNN I gave an accuracy higher than that of CNN II the authors ultimately conclude that the features extracted from CNN II are better. Why is that so? *
Your answer
[Esteva et al. 2017] How do the authors attempt to understand and interpret what the CNN has learned? What major conclusions do they reach based on their analyses? *
Your answer
[Esteva et al. 2017] (optional) The authors achieve a rather low accuracy when including the open access dermatology data. What are some of the reasons that could have contributed to that low accuracy?
Your answer
[Beck et al. 2011 & Bejnordi et al. 2017] (optional) In the Beck 2017 and the Beck 2011 readings there were classifiers built to differentiate between stroma and other types of tissues. What are the main differences between the two approaches?
Your answer
Submit
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Additional Terms