Skip to content

Commit

Permalink
added new papers
Browse files Browse the repository at this point in the history
  • Loading branch information
@rociotatiana
rociotatiana committed Dec 7, 2024
1 parent 3281c8c commit f1e5a08
Show file tree
Hide file tree
Showing 2 changed files with 133 additions and 104 deletions.
233 changes: 131 additions & 102 deletions projects/astromer/about.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -47,128 +47,157 @@

</header>

<div class="top-bar">
<div class="container">
<h1>About ASTROMER</h1>
<div class="top-bar">
<div class="container">
<h1>About ASTROMER</h1>
</div>
</div>
</div>
<div class="container">
<h3>ASTROMER Architecture</h3>
<p>ASTROMER's architecture is based on the Transformer architecture proposed in Vaswani (2017), with an
encoder-decoder Architecture.</p>
<br>
<div class="container about_astro"><img class="mx-auto about-astromer" src="static/img/astromer-arch.png" width="50%"></div>
<br>
<div class="container hidden-mobile">
<h2>Pre-trained Weights</h2>
<p>You can easily download the pre-trained weights of ASTROMER's model:</p>
<table class="table">
<thead>
<tr>
<th scope="col">Version tag</th>
<th scope="col">Pretraining Data</th>
<th scope="col">Description</th>
<th scope="col">RMSE/R-Square</th>
<th scope="col">Link</th>
</tr>
</thead>
<tbody>
<tr>
<th scope="row">v0</th>
<td>MACHO</td>
<td>Paper's model</td>
<td>0.147/0.80</td>
<td><a href="https://github.com/astromer-science/weights/raw/main/macho_a0.zip">Download</a></td>
</tr>
<tr>
<th scope="row">v1*</th>
<td>MACHO</td>
<td>Mask token and residual connections added</td>
<td>0.113/0.72</td>
<td><a href="https://github.com/astromer-science/weights/raw/main/macho_a1.zip">Download</a></td>
</tr>
</tbody>
</table>
<p>(*) Best performance up-to-date</p>
<div class="container">
<h3>ASTROMER Architecture</h3>
<p>ASTROMER's architecture is based on the Transformer architecture proposed in Vaswani (2017), with an
encoder-decoder Architecture.</p>
<br>
<div class="container about_astro"><img class="mx-auto about-astromer" src="static/img/astromer-arch.png"
width="50%"></div>
<br>
<div class="container hidden-mobile">
<h2>Pre-trained Weights</h2>
<p>You can easily download the pre-trained weights of ASTROMER's model:</p>
<table class="table">
<thead>
<tr>
<th scope="col">Version tag</th>
<th scope="col">Pretraining Data</th>
<th scope="col">Description</th>
<th scope="col">RMSE/R-Square</th>
<th scope="col">Link</th>
</tr>
</thead>
<tbody>
<tr>
<th scope="row">v0</th>
<td>MACHO</td>
<td>Paper's model</td>
<td>0.147/0.80</td>
<td><a href="https://github.com/astromer-science/weights/raw/main/macho_a0.zip">Download</a></td>
</tr>
<tr>
<th scope="row">v1*</th>
<td>MACHO</td>
<td>Mask token and residual connections added</td>
<td>0.113/0.72</td>
<td><a href="https://github.com/astromer-science/weights/raw/main/macho_a1.zip">Download</a></td>
</tr>
</tbody>
</table>
<p>(*) Best performance up-to-date</p>

</div>
<br />
</div>
<br />

<div class="container show-mobile">
<h2>Pre-trained Weights</h2>
<p>You can easily download the pre-trained weights of ASTROMER's model:</p>
<div class="accordion" id="accordionExample">
<div class="accordion-item">
<h2 class="accordion-header">
<button class="accordion-button" type="button" data-bs-toggle="collapse" data-bs-target="#collapseOne"
aria-expanded="true" aria-controls="collapseOne">
v0. MACHO
</button>
</h2>
<div id="collapseOne" class="accordion-collapse collapse show" data-bs-parent="#accordionExample">
<div class="accordion-body">
<strong>Description:</strong> Paper's model
<br>
<strong>Test RMSE:</strong> 0.147
<br>
<strong>Test R-Square:</strong> 0.80
<br>
<strong>Link:</strong> <a
href="https://github.com/astromer-science/weights/raw/main/macho_a0.zip">Download</a>
<div class="container show-mobile">
<h2>Pre-trained Weights</h2>
<p>You can easily download the pre-trained weights of ASTROMER's model:</p>
<div class="accordion" id="accordionExample">
<div class="accordion-item">
<h2 class="accordion-header">
<button class="accordion-button" type="button" data-bs-toggle="collapse" data-bs-target="#collapseOne"
aria-expanded="true" aria-controls="collapseOne">
v0. MACHO
</button>
</h2>
<div id="collapseOne" class="accordion-collapse collapse show" data-bs-parent="#accordionExample">
<div class="accordion-body">
<strong>Description:</strong> Paper's model
<br>
<strong>Test RMSE:</strong> 0.147
<br>
<strong>Test R-Square:</strong> 0.80
<br>
<strong>Link:</strong> <a
href="https://github.com/astromer-science/weights/raw/main/macho_a0.zip">Download</a>
</div>
</div>
</div>
</div>
<div class="accordion-item">
<h2 class="accordion-header">
<button class="accordion-button collapsed" type="button" data-bs-toggle="collapse"
data-bs-target="#collapseTwo" aria-expanded="false" aria-controls="collapseTwo">
v1. MACHO
</button>
</h2>
<div id="collapseTwo" class="accordion-collapse collapse" data-bs-parent="#accordionExample">
<div class="accordion-body">
<strong>Description:</strong> Mask token and residual connections added
<br>
<strong>Test RMSE:</strong> 0.113
<br>
<strong>Test R-Square:</strong> 0.72
<br>
<strong>Link:</strong> <a
href="https://github.com/astromer-science/weights/raw/main/macho_a1.zip">Download</a>
<div class="accordion-item">
<h2 class="accordion-header">
<button class="accordion-button collapsed" type="button" data-bs-toggle="collapse"
data-bs-target="#collapseTwo" aria-expanded="false" aria-controls="collapseTwo">
v1. MACHO
</button>
</h2>
<div id="collapseTwo" class="accordion-collapse collapse" data-bs-parent="#accordionExample">
<div class="accordion-body">
<strong>Description:</strong> Mask token and residual connections added
<br>
<strong>Test RMSE:</strong> 0.113
<br>
<strong>Test R-Square:</strong> 0.72
<br>
<strong>Link:</strong> <a
href="https://github.com/astromer-science/weights/raw/main/macho_a1.zip">Download</a>
</div>
</div>
</div>
<p>(*) Best performance up-to-date</p>
</div>
<p>(*) Best performance up-to-date</p>

</div>

<h2>Contributing to ASTROMER</h2>
<p>If you train your model from scratch, you can share your pre-trained weights by submitting a pull request in the
<a href="https://github.com/astromer-science/weights">weights repository.</a></p>

</div>
<h2>More information</h2>
<div class="container">
<p>You can learn more about the project in the following links:</p>
<ul>
<li>
<a href="https://arxiv.org/abs/2411.01363">
<p>Transformer-Based Astronomical Time Series Model with Uncertainty Estimation for Detecting Misclassified
Instances (2024)
</a>. Martina Cádiz-Leyton, Guillermo Cabrera-Vives, Pavlos Protopapas, Daniel Moreno-Cartagena, Cristobal
Donoso-Oliva.</p>
</li>
<li>
<p><a href="https://arxiv.org/abs/2308.06404">
Positional Encodings for Light Curve Transformers: Playing with Positions and Attention (2023)</a>. Daniel
Moreno-Cartagena, Guillermo Cabrera-Vives, Pavlos Protopapas, Cristobal Donoso-Oliva, Manuel Pérez-Carrasco,
Martina Cádiz-Leyton. </p>
</li>
<li>
<p><a href="https://arxiv.org/abs/2205.01677">ASTROMER: A transformer-based embedding for the representation of
light curves (2022)</a>. C. Donoso-Oliva, I. Becker, P. Protopapas, G. Cabrera-Vives, Vishnu M., Harsh
Vardhan.
</p>
</li>
</ul>
</div>
<div class="container hidden-mobile">
<p align="center"><iframe
src="https://docs.google.com/presentation/d/e/2PACX-1vTTqWx5v1JDfjttF5hplAZAHMifvNdY0gaLz70vrMzMpf8KdJMWrKSWZCs9GWQW_HFw9tGFS6pR-rpl/embed?start=false&loop=false&delayms=3000"
frameborder="0" width="960" height="569" allowfullscreen="true" mozallowfullscreen="true"
webkitallowfullscreen="true"></iframe></p>

<h2>Contributing to ASTROMER</h2>
<p>If you train your model from scratch, you can share your pre-trained weights by submitting a pull request on the <a
href="https://github.com/astromer-science/weights">weights repository.</a></p>
</div>
<div class="container show-mobile">
<iframe
src="https://docs.google.com/presentation/d/e/2PACX-1vTTqWx5v1JDfjttF5hplAZAHMifvNdY0gaLz70vrMzMpf8KdJMWrKSWZCs9GWQW_HFw9tGFS6pR-rpl/embed?start=false&loop=false&delayms=3000"
frameborder="0" width="400" height="299" allowfullscreen="true" mozallowfullscreen="true"
webkitallowfullscreen="true"></iframe>
</div>

</div>
<h2>More information</h2>
<p>You can learn more about the project in the following presentation:</p>
<div class="container hidden-mobile">
<p align="center"><iframe src="https://docs.google.com/presentation/d/e/2PACX-1vTTqWx5v1JDfjttF5hplAZAHMifvNdY0gaLz70vrMzMpf8KdJMWrKSWZCs9GWQW_HFw9tGFS6pR-rpl/embed?start=false&loop=false&delayms=3000" frameborder="0" width="960" height="569" allowfullscreen="true" mozallowfullscreen="true" webkitallowfullscreen="true"></iframe></p>

</div>
<div class="container show-mobile">
<iframe src="https://docs.google.com/presentation/d/e/2PACX-1vTTqWx5v1JDfjttF5hplAZAHMifvNdY0gaLz70vrMzMpf8KdJMWrKSWZCs9GWQW_HFw9tGFS6pR-rpl/embed?start=false&loop=false&delayms=3000"
frameborder="0" width="400" height="299" allowfullscreen="true" mozallowfullscreen="true" webkitallowfullscreen="true"></iframe>
</div>
</div>

</div>
<br><br><br>

<br><br><br>

<footer>
<div class="container">
<br>
<img class="footer-img" src="static/img/harvard_logo.png">
<img class="footer-img" src="static/img/udec_logo.png">
<br><br>
<br><br>
</div>
</footer>
<script src="https://cdn.jsdelivr.net/npm/@popperjs/[email protected]/dist/umd/popper.min.js"
Expand Down
4 changes: 2 additions & 2 deletions projects/astromer/static/css/style.css
View file
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,7 @@ p {
color: #2e363f;
font-size: 20px;
line-height: 2rem;
text-align: center;
/*text-align: center;*/
}

button {
Expand Down Expand Up @@ -137,7 +137,7 @@ li {
margin-left: 10px;
font-family: "Kumbh Sans",sans-serif;
list-style-type: none;
text-align: center;
/*text-align: center;*/
color: #404c58;


Expand Down

0 comments on commit f1e5a08

Please sign in to comment.