Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
user:jenda:challenges [2019/04/05 12:36]
jenda [Crazy/insane stuff] +Trypophobia
user:jenda:challenges [2019/04/08 06:14] (current)
jenda blit moved to separate page
Line 40: Line 40:
   * I suck at drawing/​art/​illustrations. Create a graphic editor that interpolates poorly drawn sketches into photorealistic/​cool drawings. For example using [[https://​github.com/​phillipi/​pix2pix|pix2pix]] or [[https://​medium.com/​artists-and-machine-intelligence/​neural-artistic-style-transfer-a-comprehensive-look-f54d8649c199|artistic style transfer]] or [[https://​github.com/​NVIDIA/​vid2vid|vid2vid]].   * I suck at drawing/​art/​illustrations. Create a graphic editor that interpolates poorly drawn sketches into photorealistic/​cool drawings. For example using [[https://​github.com/​phillipi/​pix2pix|pix2pix]] or [[https://​medium.com/​artists-and-machine-intelligence/​neural-artistic-style-transfer-a-comprehensive-look-f54d8649c199|artistic style transfer]] or [[https://​github.com/​NVIDIA/​vid2vid|vid2vid]].
     * And then the same for music     * And then the same for music
 +  * [[:​user:​jenda:​blit|Compute a BLIT!]]
  
 or just pick one [[:​project:​start|here]] ;)  or just pick one [[:​project:​start|here]] ;) 
Line 49: Line 50:
     * word2vec embeddings?     * word2vec embeddings?
   * Plants [[https://​en.wikipedia.org/​wiki/​Fractionation_of_carbon_isotopes_in_oxygenic_photosynthesis|incidentally evolved]] molecular mechanism that separates C-12 and C-13 isotopes. Let's compute a protein that selectively binds U-235!   * Plants [[https://​en.wikipedia.org/​wiki/​Fractionation_of_carbon_isotopes_in_oxygenic_photosynthesis|incidentally evolved]] molecular mechanism that separates C-12 and C-13 isotopes. Let's compute a protein that selectively binds U-235!
-  * There exist image/audio patterns and [[https://​en.wikipedia.org/​wiki/​Denn%C5%8D_Senshi_Porygon#​Strobe_lights|video sequences]] that trigger seizures in some people. Take such sequence, show it to someone while recording EEG and measure how much "​unusual"​ brain activity it has generated - voilà, you now have an utility function (video) → (how good it is at causing seizures). Now use some kind of evolutionary algorithm/​optimizer/​hill-climbing to maximize this function. You might find a real-world [[https://​en.wikipedia.org/​wiki/​BLIT_(short_story)|BLIT]]! (yes, I know that optimizing a costly black-box function across video sequences is hard, but hey, the AI field solved similar hard optimizations in the last few years) 
-    * [[https://​www.biorxiv.org/​content/​early/​2018/​11/​04/​461525|This paper]] should be a good start. 
-    * And [[http://​perceive.dieei.unict.it/​deep_learning_human_mind.php|here]] they kind of build this model for humans, but don't test if it can be used to generate adversarial examples. 
-    * [[https://​keenlab.tencent.com/​en/​whitepapers/​Experimental_Security_Research_of_Tesla_Autopilot.pdf|Here]] is a paper on blackbox adversarial examples generation 
-    * [[https://​en.wikipedia.org/​wiki/​Trypophobia|Trypophobia]],​ and some of the images look similar to adversarial examples for artificial neural networks. 
 
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Noncommercial-Share Alike 4.0 International
Recent changes RSS feed Donate Powered by PHP Valid XHTML 1.0 Valid CSS Driven by DokuWiki