Train for 5 epochs with these settings:

• learning rate=0.01
• momentum=0.9
• seed=0
• no early stopping

What is the overall accuracy (enter full number with all three digits after the comma)?

Select the Street View House Numbers (SVHN) dataset. Select:

• batch size=32
• no augmentation
• validation split=0.1
• use official test set

Load the CIFAR10 preset and apply the architecture. How many trainable parameters does the model have?

Now try to increase the accuracy to at least 80% overall. You can:

• modify the architecture
• epochs
• learning rate
• momentum
• use early stopping

Include screenshots of

• the PyTorch model definiton
• the loss plot with the progress bar and selected model info
• the normalized confusion matrix and the accuracy info
• the prediction scores and class labels of 8 samples ('CNN: Predict' tab)

Do you see misclassified samples in the prediction scores? If yes, what can be said about them when looking at the top 3 probabilities that are listed?

What is the overall accuracy of the model?

Attach the ROC plot here. How are ROC plots interpreted in general and specifically for the diabetes case? Do we have a good/bad/ok model?

Load the Pima Diabetes dataset with these settings:

• seed=42
• standardize features
• 70% training split
• 15% validation/test split
• use all features in splits

Check out the PCA plot and attach the plot here. Take a look at the cumulative variance of the first two PCs. Is this value low/ok/high?

What is the recall with regard to the diabetes-positive (class 1) patients? 

Explain the recall vs. precision values of your model with respect to the diabetes positive patients .

Load the Spotify dataset. Select Hierarchical clustering with Ward linkage (leave seed at 10). On the cluster dendrogram, what would be your estimate for the number of groups in the data set? (Hint: it is not 2)

Create a hierarchical clustering model with the number of groups you detected in the dendrogram. Check out the 'Sample from Clusters' section - can you make out the musical genres that the clusters represent?