Description
Read the following article:
Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1 (January 2014), 1929–1958.
Then,
- Explain figure 1 in ‘Introduction’.
- Explain figure 2 in ‘Introduction’.
- Describe the model via figure 3 (see ‘4. Model Description’).
- Describes, in short, a procedure for training dropout neural nets (see ‘5. Learning Dropout Nets’).
- Discuss how good the model is based on results in “Table 2: Comparison of different models on MNIST.”