Implement forward pass and activation from scratch

[Thunder-Blaze]

Write pure NumPy functions for a dense layer's forward pass (Z = WX + b), and implement ReLU (for the hidden layer) and Sigmoid (for the output layer) activation functions. Test them with dummy weights and a small batch of wine data to ensure matrix shapes align perfectly.

[Ewan-Dkhar]

/assign

[mini-walkerx]

✅ Successfully assigned to @Ewan-Dkhar.

You have 3 hours to complete this issue (Deadline: Sat, 11 Apr 2026 04:54:07 GMT).

[Ewan-Dkhar]

@vennelavarshini18 I'm opening a pr for this issue and since this is just an implementation of forward pass and activation function so it's not needed to fill in the metrics right?

[mini-walkerx]

🔗 PR #16 by @Ewan-Dkhar is now linked to this assignment. The deadline timer is paused while the PR is open.

[vennelavarshini18]

yes, as this is only feed forward pass without backpropagation, there are no metrics to report

[mini-walkerx]

⚠️ PR #16 by @Ewan-Dkhar was closed without merging. The deadline timer has resumed.

[mini-walkerx]

⏰ @Ewan-Dkhar's time to complete this issue has expired. They have been unassigned. Waitlist logic will pick up the next user...