Videos shown to participants

View 1 - Code:

Traditional coding method for implementing deep learning models. As a common standard, Microsoft Visual Studio Code is used as the Python IDE. The participants were allowed to use the DL library that they are most fluent with, among the following: Keras, Tensorflow, PyTorch, Caffe.

View 2 - Tabular:

Tabular way of designing a deep learning model, as shown in Figure 4.

Task writeup given to participants

Task #1:

Implementing a 13 layer deep convolutional neural network (CNN) model on ImageNet [15] image dataset with Conv2D, Pool2D, TanH, ReLU, Flatten, Dense, and Softmax as the set of unique layers.

Task #2:

Implementing a 16 layer deep convolutional neural network (CNN) model on CIFAR-10 [21] image dataset with Conv2D, Pool2D, ReLU, Flatten, Dense, and Softmax as the set of unique layers.

Task #3:

Implementing a 6 layer deep recurrent neural network (RNN) model on text classification dataset with Embedding, LSTM, Dense, and Softmax as the set of unique layers.