Skip to content

Deep Learning - Assignment 1 - #1

Open
mchebotarov wants to merge 2 commits into
mainfrom
assignment-1
Open

mchebotarov wants to merge 2 commits into
mainfrom
assignment-1

Conversation

@mchebotarov

Copy link
Copy Markdown
Owner

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

adding code

What did you learn from the changes you have made?

Creating neural networks to learn from images or data

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

Nope

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

Yes, the material is challenging, and had to look at examples and documentation.

How were these changes tested?

Checked my test data

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

Checklist

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

@Dmytro-Bonislavskyi Dmytro-Bonislavskyi left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi,

Nice work on Assignment 1! You've successfully implemented the models, explored different configurations, and demonstrated a good understanding of the main concepts.

Assessment: Passed with comments.

Criterion Status Comments
Data preparation ✅ Correct loading, normalization, encoding, and visualization
Baseline model ✅💬 84.92% accuracy; includes additional Dense layers instead of a strictly linear model
CNN implementation ✅ Correct CNN architecture, loss, and metrics; 87.25% accuracy
Controlled experiments ✅💬 Explored different hidden-layer configurations and learning rates
Regularization ✅💬 Compared models with and without dropout
Results visualization ✅ Experimental results presented in tables
Final model ✅ Successfully trained and evaluated; 88.87% accuracy
Reflections ✅ All completed; explanations could be more detailed

Suggestions:

  • For a strictly linear baseline, use only Flatten() followed by Dense(10) without an activation.
  • When comparing hyperparameters and regularization, try changing one setting at a time while keeping the model architecture consistent. This makes it easier to understand which changes improve performance.
  • Consider adding a little more explanation to your reflections, especially about why certain configurations performed better.

Final result: ✅ Passed with comments.

Good work overall! These are suggestions for future improvement and don't require resubmission. Your Assignment 1 is complete, and you may merge your PR.

Best,
Dmytro

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants