Skip to content

Instantly share code, notes, and snippets.

@xxMAKMAKxx

xxMAKMAKxx/gist-reveal.it-slides.html

Forked from ryanj/gist-reveal.it-slides.html
Last active February 18, 2016 00:39
Show Gist options
  • Save xxMAKMAKxx/80bc505b0961e33ca6f6 to your computer and use it in GitHub Desktop.
Save xxMAKMAKxx/80bc505b0961e33ca6f6 to your computer and use it in GitHub Desktop.
Download ZIP
Use Docker, gist.github.com, and Reveal.js to produce themed slideshow presentations for conferences and / or hackathons
Raw
gist-reveal.it-slides.html
<section data-background-transition='slide' data-transition='slide' data-state='blackout'>
<h1>Hi guys!</h1>
<h2 class='fragment'>Welcome to my fast introduction to neural networks.</h2>
</section>
<section data-background-transition='slide' data-transition='slide' data-state='blackout'>
<h1>What is the neural network exactly?</h1>
<p class='fragment'>Neural network is a system of programs and data structures that approximates the operation of the human brain.</p>
<p class='fragment'>Very simply said it will take input data, add weights to them and put it through function to make output.</p>
</section>
<section data-background-transition='slide' data-transition='slide' data-state='blackout'>
<section>
<h1>Let's watch some introduction to neural networks.</h1>
<p class='fragment'>http://maksp.xf.cz/video.mp4</p>
</section>
</section>
<section data-background-transition='slide' data-transition='slide' data-state='blackout'>
<section>
<h1>Neural networks are for:</h1>
<p class='fragment'>A: pattern recognition / classification</p>
<p class='fragment'>B: function approximation / regression</p>
</section>
<section>
<h2>Real use cases:</h2>
<ul>
<li class='fragment'>Character Recognition - handwriting</li>
<li class='fragment'>Image compression</li>
<li class='fragment'>Predictions - weather/market and more</li>
<li class='fragment'>Miscellaneous Applications</li>
</ul>
</section>
<section>
<h1>Miscellaneous Applications</h1>
<h4 class='fragment'>Getting rat thoughts to move robotic parts</h4>
<p class='fragment'>1. Train a rat to press a lever, which activates a robotic arm. Robotic arm delivers reward to rat.</p>
<p class='fragment'>2. Attach a 16-probe array to the rat's brain that can record the activity of 30 neurons at once.</p>
</section>
<section>
<p class='fragment'>3. Train a neural network program to recognize brain-activity patterns during a lever press.</p>
<p class='fragment'>4. Neural network can predict movement from the rat's brain activity alone, so when the rat's brain activity indicates that it is about to press the lever, robotic arm moves and rewards the rat - the rat does not need to press the lever, but merely needs to "think" about doing so </p>
</section>
<section>
<h1>Image filters</h1>
<p class='fragment'>Another usage can be used within image filters</p>
<p class='fragment'>http://synaptic.juancazala.com/#/image-filters</p>
</section>
</section>
<section>
<section>
<h1>So - ultimate question:</h1>
<p class='fragment'>Is our project on of the use cases for neural networks?</p>
<h4 class='fragment'>IMHO no :/</h4>
</section>
<section>
<h1>Questions? :)</h1>
</section>
</section>
<section>
<p>Also, I have noticed one problem - it is not easy to focus on both algorithm and learning new framework</p>
<p class='fragment'>My suggestion for next time is to distribute this work among me and Franta</p>
<p class='fragment'>One will study algorithm, the other will study node.js</p>
</section>
Raw
push_script
git add .
git commit -m 'Another slide change'
git push
Raw
video.mp4
This file has been truncated, but you can view the full file.
View raw
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment