DOC: Adds Iñigo's w10 and w11 blog posts #63
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Also adds necessary images
Previously 100dpi, now 600dpi
itellaetxe
requested review from
jhlegarreta,
skoudoro,
pjsjongsung,
WassCodeur,
robinroy03 and
deka27
|
🪓 PR closed, deleted preview at https://github.com/dipy/preview-html/tree/main/dipy.org/pull/63/ |
itellaetxe
changed the title
WassCodeur
reviewed
Aug 13, 2024
WassCodeur
approved these changes
Aug 13, 2024
robinroy03
approved these changes
Aug 13, 2024
pjsjongsung
approved these changes
Aug 13, 2024
jhlegarreta
reviewed
Aug 14, 2024
|
|
||
| Let's break down how the AAE works. For those not familiar with how generative adversarial networks (GANs) work, the idea is to have two networks, a generator and a discriminator, that play a game. The generator tries to generate samples that look like the real data (e.g.: pictures of animals), while the discriminator tries to distinguish between real and generated samples. The generator is trained to fool the discriminator, and the discriminator is trained to not be fooled. This way, the generator learns to generate samples that look like the real data. The adversarial loss (:math:`\mathcal{L}_{adv}`) is computed as it is shown in the lowest rectangle. | ||
|
|
||
| In our case, the generator is the encoder :math:`\mathcal{G}`, which generates a latent representation of the input data, which the discriminator :math:`\mathcal{D}` tries to distinguish from "real" latent representations, sampled from a given prior distribution. The trick to introduce the information of the kind of animal to which the photo belongs to is to concatenate the latent representation with the one-hot encoded bundle and attribute vectors. This way, the decoder :math:`\mathcal{D}` can generate samples conditioned on a categorical variable. The reconstruction loss (:math:`\mathcal{L}_{MSE}`) is computed as it is shown in the middle rectangle, and it ensures that the samples are reconstructed from the latent representation as close as possible to the original data. |
There was a problem hiding this comment.
The trick to introduce the information of the kind of animal to which the photo belongs (...) the one-hot encoded bundle (...) : talking about photos, then bundles, previously about pictures of animals. Can we be consistent when choosing the example domain?
There was a problem hiding this comment.
Oops, true. Will stick to animals to keep it simple.
|
|
||
| In our case, the generator is the encoder :math:`\mathcal{G}`, which generates a latent representation of the input data, which the discriminator :math:`\mathcal{D}` tries to distinguish from "real" latent representations, sampled from a given prior distribution. The trick to introduce the information of the kind of animal to which the photo belongs to is to concatenate the latent representation with the one-hot encoded bundle and attribute vectors. This way, the decoder :math:`\mathcal{D}` can generate samples conditioned on a categorical variable. The reconstruction loss (:math:`\mathcal{L}_{MSE}`) is computed as it is shown in the middle rectangle, and it ensures that the samples are reconstructed from the latent representation as close as possible to the original data. | ||
|
|
||
| As for the AR, we try to tie a continuous attribute of choice found in the data space (fur length, age, size, etc.) to a specific dimension of the latent space. To do this, we compute an attribute-distance matrix in the data space :math:`D_a`, and we compute a distance matrix from the chosen dimension of the latent space (:math:`D_r`). By minimizing the mean absolute error (MAE) between the two matrices, we force the latent space to be organized in such a way that the chosen dimension is related to the chosen attribute. This way, we can generate samples conditioned on the attribute of choice. The AR loss (:math:`\mathcal{L}_{AR}`) is computed as it is shown in the top rectangle. |
There was a problem hiding this comment.
Related to the above: (fur length, age, size, etc.)
There was a problem hiding this comment.
Got it, thanks :)
deka27
approved these changes
Aug 14, 2024
jhlegarreta
approved these changes
Aug 14, 2024
skoudoro
approved these changes
Aug 14, 2024
github-actions bot
added a commit
that referenced
this pull request
Aug 14, 2024
DOC: Adds Iñigo's w10 and w11 blog posts 95ccd31
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds Iñigo's week 10 and week 11 blog posts.
Also adds necessary images to render properly.
I tried the inline LaTeX capabilities of RST in w11 blog post, should render fine (I believe).