Ctrl+K

Reading 16: Classification III: Neural Networks, Evaluating Classifiers

Reading 16: Classification III: Neural Networks, Evaluating Classifiers#

For the class on Monday, April 1st

Reading assignments#

  1. Read the following sections of [ICVG20]:

    • Sec. 9.8 “Deep Learning and Neural Networks”

      • Sec. 9.8.1 “Neural Networks”

      • Sec. 9.8.2 “Training the Network”

      • Sec. 9.8.3 “How Many Layers and How Many Neurons?”

      • Sec. 9.8.4 “Convolutional Networks”

      • (Optional) Sec. 9.8.5 “Autoencoders”

    • Sec. 9.9 “Evaluating Classifiers: ROC Curves”

    • Sec. 9.10 “Which Classifier Should I Use?”

Questions#

Hint

Submit your answer on Canvas. Due at noon, Monday, April 1st.

  1. List anything from your reading that confuses you. Explain why they confuse you. You are strongly encouraged to think about what questions you have about the reading, but if you really have no questions at all, please briefly summarize what you have learned from this reading assignment.

  2. Use your own words to breifly explain what an “activation function” is in the context of neural networks

  3. What quantities does an ROC curve plot against each other?

Discussion Preview#

Note

We will discuss the following questions in class. They are included here so that you have a chance to think about them before class. You need not submit your answers as part of this assignment.

  1. We will discuss neural networks and its applications.

  2. We will continue to compare different classification methods.

  3. We will discuss how to evaluate classifiers in different use cases.

Contents