Difference between revisions of "Team:SEU/Improve"

(Prototype team page)
 
 
(5 intermediate revisions by the same user not shown)
Line 1: Line 1:
−
{{SEU}}
+
{{SEU/Header}}
 
<html>
 
<html>
 +
<head><script src="https://2019.igem.org/common/MathJax-2.5-latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script></head>
 +
<style>
 +
.buttonContri {
 +
    background-color: #4CAF50 !important;
 +
    border: none !important;
 +
    color: white !important;
 +
    padding: 16px 32px !important;
 +
    text-align: center !important;
 +
    text-decoration: none !important;
 +
    display: inline-block !important;
 +
    font-size: 16px !important;
 +
    margin: 4px 2px !important;
 +
    cursor: pointer !important;
 +
}
  
−
 
+
.about-contentbox1 {
−
<div class="column full_size judges-will-not-evaluate">
+
  margin-top: 80px;
−
<h3>★  ALERT! </h3>
+
  text-align:left;
−
<p>This page is used by the judges to evaluate your team for the <a href="https://2019.igem.org/Judging/Medals">medal criterion</a> or <a href="https://2019.igem.org/Judging/Awards"> award listed below</a>. </p>
+
  line-height:1.8;
−
<p> Delete this box in order to be evaluated for this medal criterion and/or award. See more information at <a href="https://2019.igem.org/Judging/Pages_for_Awards"> Instructions for Pages for awards</a>.</p>
+
}
 +
.about-contentbox1 span {
 +
  font-size: 24px;
 +
  font-weight: 300;
 +
}
 +
.about-contentbox1 h1 {
 +
  font-size: 40px;
 +
  font-weight: 700;
 +
}
 +
.about-contentbox1 h2 {
 +
  font-size: 36px;
 +
  font-weight: 700;
 +
}
 +
.about-contentbox1 h3 {
 +
  font-size: 32px;
 +
  font-weight: 700;
 +
}
 +
.about-contentbox1 h4 {
 +
  font-size: 24px;
 +
  font-weight: 700;
 +
}
 +
.about-contentbox1 h5 {
 +
  font-size: 20px;
 +
  font-weight: 700;
 +
}
 +
.about-contentbox1 p {
 +
  max-width: 820px;
 +
  text-align: left !important;
 +
  line-height: 2;
 +
  font-weight:250;
 +
  font-size: 20px !important;
 +
}
 +
.img-float-right{
 +
  float:right;
 +
}
 +
.img-float-left{
 +
  float: left;
 +
}
 +
</style>
 +
<div id="fullpage" class="fullpage-default">
 +
    <div>
 +
        <div class="section-inner">
 +
            <div class="about-section">
 +
                <div class="row justify-content-center">
 +
                    <div>
 +
                        <div class="row">
 +
                          <div class="row justify-content-center">
 +
                              <div>
 +
                                  <div class="about-contentbox1">
 +
                                      <div>
 +
                                          <h1>Improve</h1>
 +
                                          <p>This is our first time to participate in iGEM. According to our survey, there is few similar projects in previous iGEM competition hence our focus in this project lies in improving state-of-the-art molecular neural networks in literature [1].</p>
 +
                                          <p>In [1], the values of input signals of neural networks are binary i.e. the values are constrained to be either 0 or 1, which limits the application in real world. In computer science applications, data are usually real numbers. In addition, training, which is one critical part of artificial intelligence systems, has not been integrated to the molecular system in [1]. Therefore we make such improvements:</p>
 +
                                          <p>1. We support continuous value computation in our molecular systems. CPU/GPU-based software applications can be possibly mapped to our system based on this feature. There is a pattern recognition example in <a href="https://2019.igem.org/Team:SEU/Demonstrate"></a>Demonstrate Page.</a> </p>
 +
                                          <p>2. We integrate training to our neural networks. Therefore our system does not require in silico training processes.</p>
 +
                                          <p>Also, we develop a <a href="https://2019.igem.org/Team:SEU/Software"><b>Software Tool</b></a>to help other researchers design their own systems.</p>
 +
                                          <h3>Reference</h3>
 +
                                          <p>[1] K. Cherry, L. Qian, "Scaling up molecular pattern recognition with DNA-based winner-take-all neural networks," Nature, vol. 559, no. 7714, pp.370-376, 2018.</p>
 +
                                </div>
 +
                              </div>
 +
                          </div>
 +
                        </div>
 +
                    </div>
 +
                </div>
 +
            </div>
 +
        </div>
 +
    </div>
 
</div>
 
</div>
−
 
−
 
−
<div class="clear"></div>
 
−
 
−
 
−
<div class="column full_size">
 
−
<h1>Improve a Previous Part or Previous Project</h1>
 
−
<p>For teams seeking to improve upon a previous part or project, you should document all of your work on this page. Please remember to include all part measurement and characterization data on the part's main page on the Registry. Please include a link to your improved part's Registry page on this page.</p>
 
−
 
−
<h3>Gold Medal Criterion #2</h3>
 
−
<p><b>Improve a Previous Part - Standard Tracks:</b> Convince the judges that you have created a new BioBrick Part that has a functional improvement upon an existing BioBrick Part. You must perform experiments with both parts to demonstrate this improvement. Clearly document the quantitative experimental characterization data on the Part's Main Page on the Registry for both the existing and new parts (see the <a href="http://parts.igem.org/Help:Document_Parts">Registry Document Parts page</a> for instructions).
 
−
<br><br>
 
−
Both the existing and new part must be <a href="http://parts.igem.org/Help:Standards/Assembly/RFC10">RFC10</a> or Type IIS compatible. The sequences of the new and existing parts must be different. The existing part must NOT be from your 2019 part number range and must be different from the part you used in Bronze #4. The new part you create must also be different from the new part documented in Silver #1. Please see the <a href="https://2019.igem.org/Measurement/Resources">Measurement Resources page</a> for more information about experimental characterization data.
 
−
<br><br>
 
−
<b>Improve a Previous Project - Special Tracks:</b> Improve the function of an existing iGEM project (that your current team did not originally create) and display your achievement on your wiki.</p>
 
−
 
−
 
 
</div>
 
</div>
−
 
−
 
−
 
 
</html>
 
</html>

Latest revision as of 13:45, 18 October 2019





Improve

This is our first time to participate in iGEM. According to our survey, there is few similar projects in previous iGEM competition hence our focus in this project lies in improving state-of-the-art molecular neural networks in literature [1].

In [1], the values of input signals of neural networks are binary i.e. the values are constrained to be either 0 or 1, which limits the application in real world. In computer science applications, data are usually real numbers. In addition, training, which is one critical part of artificial intelligence systems, has not been integrated to the molecular system in [1]. Therefore we make such improvements:

1. We support continuous value computation in our molecular systems. CPU/GPU-based software applications can be possibly mapped to our system based on this feature. There is a pattern recognition example in Demonstrate Page.

2. We integrate training to our neural networks. Therefore our system does not require in silico training processes.

Also, we develop a Software Toolto help other researchers design their own systems.

Reference

[1] K. Cherry, L. Qian, "Scaling up molecular pattern recognition with DNA-based winner-take-all neural networks," Nature, vol. 559, no. 7714, pp.370-376, 2018.