Question 1Which of the following do you typically see in a ConvNet? (Check all that apply.)

In a Convolutional Neural Network (ConvNet), you typically see the following components:

1. Convolutional Layers - These layers apply convolutional filters to extract features from the input images.
2. Pooling Layers - These layers down-sample the feature maps to reduce their dimensionality and retain the most important information.
3. Activation Functions - Such as ReLU (Rectified Linear Unit), are used to introduce non-linearity into the model.
4. Fully Connected Layers - These layers are often at the end of the network and are used for classification tasks, taking the features identified by the previous layers and making the final predictions.
5. Batch Normalization - This technique is used to stabilize and accelerate the training process by normalizing the inputs to each layer.
6. Dropout Layers - These are used to prevent overfitting by randomly setting a portion of the neurons to zero during training.

Hence, in a ConvNet, you can typically expect to see convolutional layers, pooling layers, activation functions, fully connected layers, and possibly batch normalization and dropout layers.