Assignment 1

[davidancor]

UofT-DSI | Deep Learning - Assignment 1

What changes are you trying to make? (e.g. Adding or removing code, refactoring existing code, adding reports)

Implemented a vision model pipeline for Fashion MNIST classification using Keras

• Added data loading, normalization, and one-hot encoding
• Built a baseline linear model (Flatten + Dense) as a benchmark
• Built a simple CNN with Conv2D layers
• Ran controlled experiments on:
• Hyperparameter: number of Conv2D layers (1 vs 2)
• Regularization: L2 regularization, MaxPooling2D, and Dropout
• Trained a final model using the best-performing setup
• Added reflections and analysis of the results
• What did you learn from the changes you have made?
• CNNs vs linear models: Convolutions capture spatial structure and improve accuracy (84.5% → 90.2%)
• Overfitting: Extra Conv2D layers increased training accuracy (~97%) but not test accuracy (~90%), indicating memorization
• MaxPooling: Reduced spatial resolution and encouraged more general features, improving test accuracy to ~91.3%
• Regularization: Dropout helped more than L2 here; L2 had little effect
• Validation split: Using validation_split=0.1 helped monitor overfitting during training

What did you learn from the changes you have made?

Was there another approach you were thinking about making? If so, what approach(es) were you thinking of?

Were there any challenges? If so, what issue(s) did you face? How did you overcome it?

How were these changes tested?

A reference to a related issue in your repository (if applicable)

Checklist

• [ x ] I can confirm that my changes are working as intended

[github-actions]

Hello, thank you for your contribution. If you are a participant, please close this pull request and open it in your own forked repository instead of here. Please read the instructions on your onboarding Assignment Submission Guide more carefully. If you are not a participant, please give us up to 72 hours to review your PR. Alternatively, you can reach out to us directly to expedite the review process.