22.02.2024 Views

Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

What does our model look like? Visualization always helps, so here we go.

Figure 4.4 - Yet another logistic regression

"Wait, where is the bias?"

I am glad you noticed. I removed it on purpose! I want to illustrate the difference

between a shallow model like this and a deeper one, and it is much easier to work it

out if we ditch the bias. Moreover, I would also like to recall the corresponding

notation for our model, since I am planning on using this notation to illustrate that

point.

Notation

The vectorized representations of the weights (W) and features (X) are:

Shallow Model | 299

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!