Phil 10.27.17

7:00 – 5:00 ASRC MKT

  • Nicely written paper on GANs:
    • Abstract: We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CELEBA images at 10242. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally,we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CELEBA dataset.
    • With cool video
    • And code
  • Working on adding UI and batch interaction for the adversarial herding
    • Enable/disable switch – Done
    • Field for power – don’t know what the scale should be so no slider yet – Done
    • Set<String, Set<Flockingshape, weight>> If this doesn’t work, make shape comparable by name. Done!
      HashMap<FlockingShape, Double> alignedShapeMap;
      if(flock.size() > 0 && !alignedFlockMap.containsKey(flockName)){
          alignedShapeMap = new HashMap<>();
          alignedFlockMap.put(flockName, alignedShapeMap);
          alignedShapeMap = alignedFlockMap.get(flockName);
    • Do I want to delay the triggering of the herding on a separate timer? Waiting on this.
    • It’s done, and the results are kind of scary. If I set the weight of the herder to 15, I can change the change the flocking behavior of the default to echo chamber.
    • Normal: No Herding
    • Herding weight set to 15, other options the same: HerdingWeight15
  • Did some additional tweaking to see if having highly-weighted herders ignore each other (they would be coordinated through C&C) would have any effect. It doesn’t. There is enough interaction through the regular populations to keep the alignment space reduced.
  • It looks like there is a ‘sick echo chamber’ pattern. If the borders are reflective, and the herding weight + influence radius is great enough, then a wall-hugging pattern will emerge.
    • The influence weight is sort of a credibility score. An agent that has a lot of followers, or says a lot of the things that I agree with has a lot of influence weight The range weight is reach.
    • Since a troll farm or botnet can be regarded as a single organization,  interacting with any one of the agents is really interacting with the root entity.  So a herding agent has high influence and high reach. The high reach explains the border hugging behavior.
    • It’s like there’s someone at the back of the stampede yelling YOUR’E GOING THE RIGHT WAY! KEEP AT IT! And they never go off the cliff because they are a swarm Or, it never goes of the cliff, because it manifests as a swarm.
    • A loud, distributed voice pointing in a bad direction means wall hugging. Note that there is some kind of floating point error that lets wall huggers creep off the edge.Edgecrawling
    • With a respawn border, we get the situation where the overall heading of the flock doesn’t change even as it gets destroyed as it goes over the border. Again, since the herding algorithm is looking at the overall population, it never crosses the border but influences all the respawned agents to head towards the same edge: DirectionPreserving
  • Paper thoughts:
    • Armys have different patterns from emergent groups. They are imposed formations and reflect a commander’s will
    • From a distance, they look different, but close up, they may look the same. One of the reasons for the success of the Roman Legion was the use of formations against the less sophisticated structures of their adversaries [ref]