Skip to content

Update index.html #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ferdavid1 merged 1 commit into from
Nov 5, 2017
Merged

Update index.html #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion posts/2015-09-NN-Types-FP/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ <h2 id="representations-are-types">Representations are Types</h2>
A layer <span class="math">\(f_1\)</span> followed by a layer <span class="math">\(f_2\)</span>. The output representation of <span class="math">\(f_1\)</span> is the input of <span class="math">\(f_2\)</span>.
</div>
<p>In the case of very simple neural network architectures, where there’s just a linear sequence of layers, this isn’t very interesting. The representation of one layer’s output needs to match the representation of the next layer’s input – so what? It’s a trivial and boring requirement.</p>
<p>But many neural networks have more complicated architectures where this becomes a more interesting constraint. For a very simple example, let’s imagine a neural network with multiple similar kinds of inputs, which performs multiple, related tasks. Perhaps it takes in RGB images and also grayscale images. Maybe it’s looking at pictures of people, and trying to predict age and gender. Because the similarities between the kinds of inputs and between the kinds of tasks, it can be helpful to do all of this in one model, so that training data helps them all. The result is multiple input layers mapping into one representation, and multiple outputs mapping from the same representation.</p>
<p>But many neural networks have more complicated architectures where this becomes a more interesting constraint. For a very simple example, let’s imagine a neural network with multiple similar kinds of inputs, which performs multiple, related tasks. Perhaps it takes in RGB images and also grayscale images. Maybe it’s looking at pictures of people, and trying to predict age and gender. Because of the similarities between the kinds of inputs and between the kinds of tasks, it can be helpful to do all of this in one model, so that training data helps them all. The result is multiple input layers mapping into one representation, and multiple outputs mapping from the same representation.</p>
<div style="width:80%; margin-left:auto; margin-right:auto; margin-bottom:5px; margin-top:17px;">
<img src="img/types-branchmerge.png" alt>
</div>
Expand Down