Category Archives: Simulation

Phil 10.17.18

7:00 – 4:00 Antonio Workshop

Phil 10.8.18

7:00 – 12:00, 2:00 – 5:00 ASRC Research

  • Finish up At Home in the Universe notes – done!
  • Get started on framing out Antonio’s paper – good progress!
    • Basically, Aaron and I think there is a spectrum of interaction that can occur in these systems. At one end is some kind of market, where communication is mediated through price, time, and convenience to the transportation user. At the other is a more top down, control system way of dealing with this. NIST RCS would be an example of this. In between these two extremes are control hierarchies that in turn interact through markets
  • Wrote up some early thoughts on how simulation and machine learning can be a thinking fast and slow solution to understandable AI

Phil 9.28.18

7:30 – 4:00 ASRC MKT

  • Stumbled on this podcast this morning: How Small Problems Snowball Into Big Disasters
  • How to Prepare for a Crisis You Couldn’t Possibly Predict
  • I’m trying to think about how this should be applied to human/machine ecologies. I think that simulation is really important because it lets one model patch compare itself against another model without real-world impacts. This has something to do with a shared, multi-instance environment simulation as well. The environment provides one level of transparent interaction, but there also needs to be some level of inadvertent social information that shows some insight into how a particular system is working.
    • When the simulation and the real world start to diverge for a system, that needs to be signaled
    • Systems need to be able to “look into” other simulations and compare like with like. So a tagged item (bicycle) in one sim is the same in another.
    • Is there an OS that hands out environments?
    • How does a decentralized system coordinate? Is there an answer in MMOGs?
  • Kate Starbird’s presentation was interesting as always. We had a chance to talk afterwards, and she’d like to see our work, so I’ve sent her links to the last two papers.
    I also met Bill Braniff, who is the director of the UMD Study of Terrorism and responses to Terrorism. He got papers too, with a brief description about how mapping could aid in the detection of radicalization patterns
    Then at lunch, I had a chance to meet with Roger Bostelman from NIST. He’s interested in writing standards for fleet and swarm vehicles, and is interested in making sure that standards mitigate the chance of stampeding autonomous vehicles, so I sent him the Blue Sky draft.
    And lastly, I got a phone call from Aaron who says that our project will be terminated December 31, after which there will be no more IR&D at ASRC. It was a nice run while it lasted. And they may change their minds, but I doubt it.

Phil 9.21.18

7:00 – 4:00 ASRC MKT

  • “Who’s idea was it to connect every idiot on the internet with every other idiot” PJ O’Rourke, Commonwealth Club, 2018
  • Running Programs In Reverse for Deeper A.I.” by Zenna Tavares
    • In this talk I show that inverse simulation, i.e., running programs in reverse from output to input, lies at the heart of the hardest problems in both human cognition and artificial intelligence. How humans are able to reconstruct the rich 3D structure of the world from 2D images; how we predict that it is safe to cross a street just by watching others walk, and even how we play, and sometimes win at Jenga, are all solvable by running programs backwards. The idea of program inversion is old, but I will present one of the first approaches to take it literally. Our tool ReverseFlow combines deep-learning and our theory of parametric inversion to compile the source code of a program (e.g., a TensorFlow graph) into its inverse, even when it is not conventionally invertible. This framework offers a unified and practical approach to both understand and solve the aforementioned problems in vision, planning and inference for both humans and machines.
  • Bot-ivistm: Assessing Information Manipulation in Social Media Using Network Analytics
    • Matthew Benigni 
    • Kenneth Joseph
    • Kathleen M. Carley (Scholar)
    • Social influence bot networks are used to effect discussions in social media. While traditional social network methods have been used in assessing social media data, they are insufficient to identify and characterize social influence bots, the networks in which they reside and their behavior. However, these bots can be identified, their prevalence assessed, and their impact on groups assessed using high dimensional network analytics. This is illustrated using data from three different activist communities on Twitter—the “alt-right,” ISIS sympathizers in the Syrian revolution, and activists of the Euromaidan movement. We observe a new kind of behavior that social influence bots engage in—repetitive @mentions of each other. This behavior is used to manipulate complex network metrics, artificially inflating the influence of particular users and specific agendas. We show that this bot behavior can affect network measures by as much as 60% for accounts that are promoted by these bots. This requires a new method to differentiate “promoted accounts” from actual influencers. We present this method. We also present a method to identify social influence bot “sub-communities.” We show how an array of sub-communities across our datasets are used to promote different agendas, from more traditional foci (e.g., influence marketing) to more nefarious goals (e.g., promoting particular political ideologies).
  • Pinged Aaron M. about writing an article
  • More iConf paper. Got a first draft on everything but the discussion section

Phil 8.30.18

7:00 – 5:00  ASRC MKT

  • Target Blue Sky paper for iSchool/iConference 2019: The chairs are particularly looking for “Blue Sky Ideas” that are open-ended, possibly even “outrageous” or “wacky,” and present new problems, new application domains, or new methodologies that are likely to stimulate significant new research. 
  • I’m thinking that a paper that works through the ramifications of this diagram as it relates to people and machines. With humans that are slow responding with spongy, switched networks the flocking area is large. With a monolithic densely connected system it’s going to be a straight line from nomadic to stampede. Nomad-Flocking-Stampede2
    • Length: Up to 4 pages (excluding references)
    • Submission deadline: October 1, 2018
    • Notification date: mid-November, 2018
    • Final versions due: December 14, 2018
    • First versions will be submitted using .pdf. Final versions must be submitted in .doc, .docx or La Tex.
  • More good stuff on BBC Business Daily Trolling for Cash
    • Anger and animosity is prevalent online, with some people even seeking it out. It’s present on social media of course as well as many online forums. But now outrage has spread to mainstream media outlets and even the advertising industry. So why is it so lucrative? Bonny Brooks, a writer and researcher at Newcastle University explains who is making money from outrage. Neuroscientist Dr Dean Burnett describes what happens to our brains when we see a comment designed to provoke us. And Curtis Silver, a tech writer for KnowTechie and ForbesTech, gives his thoughts on what we need to do to defend ourselves from this onslaught of outrage.
  • Exposure to Opposing Views can Increase Political Polarization: Evidence from a Large-Scale Field Experiment on Social Media
    • Christopher Bail (Scholar)
    • There is mounting concern that social media sites contribute to political polarization by creating “echo chambers” that insulate people from opposing views about current events. We surveyed a large sample of Democrats and Republicans who visit Twitter at least three times each week about a range of social policy issues. One week later, we randomly assigned respondents to a treatment condition in which they were offered financial incentives to follow a Twitter bot for one month that exposed them to messages produced by elected officials, organizations, and other opinion leaders with opposing political ideologies. Respondents were re-surveyed at the end of the month to measure the effect of this treatment, and at regular intervals throughout the study period to monitor treatment compliance. We find that Republicans who followed a liberal Twitter bot became substantially more conservative post-treatment, and Democrats who followed a conservative Twitter bot became slightly more liberal post-treatment. These findings have important implications for the interdisciplinary literature on political polarization as well as the emerging field of computational social science.
  • Setup gcloud tools on laptop – done
  • Setup Tensorflow on laptop. Gave up un using CUDA 9.1, but got tf doing ‘hello, tensorflow’
  • Marcom meeting – 2:00
  • Get the concept of behaviors being a more scalable, dependable way of vetting information.
    • Eg Watching the DISI of outrage as manifested in trolling
      • “Uh. . . . not to be nitpicky,,,,,but…the past tense of drag is dragged, not drug.”: An overview of trolling strategies
        • Dr Claire Hardaker (Scholar) (Blog)
          • I primarily research aggression, deception, and manipulation in computer-mediated communication (CMC), including phenomena such as flaming, trolling, cyberbullying, and online grooming. I tend to take a forensic linguistic approach, based on a corpus linguistic methodology, but due to the multidisciplinary nature of my research, I also inevitably branch out into areas such as psychology, law, and computer science.
        • This paper investigates the phenomenon known as trolling — the behaviour of being deliberately antagonistic or offensive via computer-mediated communication (CMC), typically for amusement’s sake. Having previously started to answer the question, what is trolling? (Hardaker 2010), this paper seeks to answer the next question, how is trolling carried out? To do this, I use software to extract 3,727 examples of user discussions and accusations of trolling from an eighty-six million word Usenet corpus. Initial findings suggest that trolling is perceived to broadly fall across a cline with covert strategies and overt strategies at each pole. I create a working taxonomy of perceived strategies that occur at different points along this cline, and conclude by refining my trolling definition.
        • Citing papers
  • FireAnt (Filter, Identify, Report, and Export Analysis Toolkit) is a freeware social media and data analysis toolkit with built-in visualization tools including time-series, geo-position (map), and network (graph) plotting.
  • Fix marquee – done
  • Export to ppt – done!
    • include videos – done
    • Center title in ppt:
      • model considerations – done
      • diversity injection – done
  • Got the laptop running Python and Tensorflow. Had a stupid problem where I accidentally made a virtual environment and keras wouldn’t work. Removed, re-connected and restarted IntelliJ and everything is working!

Phil 8.19.18

7:00 – 5:30 ASRC MKT

  • Had a thought that the incomprehension that comes from misalignment that Stephens shows resembles polarizing light. I need to add a slider that enables influence as a function of alignment. Done
    • Getting the direction cosine between the source and target belief
      double interAgentDotProduct = unitOrientVector.dotProduct(otherUnitOrientVector);
      double cosTheta = Math.min(1.0, interAgentDotProduct);
      double beliefAlignment = Math.toDegrees(Math.acos(cosTheta));
      double interAgentAlignment = (1.0 - beliefAlignment/180.0);
    • Adding a global variable that sets how much influence (0% – 100%) influence from an opposing agent. Just setting it to on/off, because the effects are actually pretty subtle
  • Add David’s contributions to slide one writeup – done
  • Start slide 2 writeup
  • Find casters for Dad’s walker
  • Submit forms for DME repair
    • Drat – I need the ECU number
  • Practice talk!
    • Need to reduce complexity and add clearly labeled sections, in particular methods
  • I need to start paying attention to attention
  • Also, keeping this on the list How social media took us from Tahrir Square to Donald Trump by Zeynep Tufekci
  • Social Identity Threat Motivates Science – Discrediting Online Comments
    • Experiencing social identity threat from scientific findings can lead people to cognitively devalue the respective findings. Three studies examined whether potentially threatening scientific findings motivate group members to take action against the respective findings by publicly discrediting them on the Web. Results show that strongly (vs. weakly) identified group members (i.e., people who identified as “gamers”) were particularly likely to discredit social identity threatening findings publicly (i.e., studies that found an effect of playing violent video games on aggression). A content analytical evaluation of online comments revealed that social identification specifically predicted critiques of the methodology employed in potentially threatening, but not in non-threatening research (Study 2). Furthermore, when participants were collectively (vs. self-) affirmed, identification did no longer predict discrediting posting behavior (Study 3). These findings contribute to the understanding of the formation of online collective action and add to the burgeoning literature on the question why certain scientific findings sometimes face a broad public opposition.

Phil 7.18.18

divylmzuyaeqjbk

There was no colusion“…”Anyone involved in that meddling to justice.

Premises for Data Science Magical Realism

  • What follows are some premises for data science magical realism stories based (very, very loosely) on experiences I’ve had or heard about — premises, that is, for stories about impossible, absurd, magical things happening to data scientists in ordinary data science situations. Enjoy!
  • More from David Masad

Program Synthesis in 2017-18

  • A high-level overview of the recent ideas and representative papers in program synthesis as of mid-2018.
  • Alex (Oleksandr) Polozov, a researcher in the Deep Procedural Intelligence group at Microsoft Research AI, Redmond. I work on neural program synthesis from input-output examples and natural language, intersections of machine learning and software engineering, and neuro-symbolic architectures. I am particularly interested in combining neural and symbolic techniques to tackle the next generation of AI problems, including program synthesis, planning, and reasoning.

UMAP Uniform Manifold Approximation and Projection for Dimension Reduction | SciPy 2018 |(video) (paper)

  • UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP as described has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.
  • This could be nice for building maps

7:00 – 5:00 ASRC MKT

  • Progress on getting my keys back!
  • Got everyone’s response on the Doodle, but only 4 of the 5 line up…
  • Finish first pass through PhD review slides
  • Start SASO slides and poster?
  • Continue with exporting terms from the sim and importing them into python. One of the things that will matter is the tagging of the data with the seed terms from the sim as well as the cell name so that reconstructions can be compared for accuracy.
  • Added the cell location to each <sampleData> so that there can be some kind of tagging/ground truth about the maps we’re inferring.
  • Working on iterating through the etree hierarchy. I can now read in the file, parse it and get elements that I’m looking for.
  • Tomorrow will be pulling the seed words out of the code in an ordered list. Generated sentences will need to be timestamped to that conversations can be reconstructed. That being said, it could be interesting to take seed words out of a generated sentence and add them to the embedding seed words. Something to think about.

Phil 6.22.18

7:00 – 5:30 ASRC MKT

  • Twitter experiment on a fake Gary Indiana secession. IFTTT retweeting leads to interesting behavior.
  • Fixed FlockingShape casting by adding a customDrawStep(GraphicsContext gc) to the SmartShape base class that’s called from draw().
  • Add records to each agent that store a list of source and agent influences at each time sample. It should include the name of the item and the amount of influence. Probably save as an XML file, since it has too many dimensions. The file could then be used to create terms or spreadsheets.
    • Started on CAInfluence class which will be added to CA classes in an arrayList in BaseCA;
  • More file conversion with Bob – and everything worked great until I try one after Bob leaves. Ka-BOOM!
    • Installed all the packages to get everything to run in the debugger. Found what appears to be a perfectly good line “range” that causes the problem? Will start debugging on Wednesday.
  • Project MERCATOR proposal
  • Meeting with Sy

Phil 6.21.18

7:00 – 4:00 ASRC MKT

  • Add an attractor scalar for agents that’s normally zero. A vector to each agent within the SIH is calculated and scaled by the attractor scalar. That vector is then added to the direction vector to the agent – done
  • Remove the heading influence based on site – done
  • Add a white circle to the center of the agent that is the size of the attraction scalar. Done
  • Add attraction radius slider that is independent of the SIH. -done
  • Add a ‘site trajectory’ to the spreadsheet that will have the site lists (and their percentage?)
  • There is now an opportunity for a poster and a demo at SASO
  • Add stories, lists and maps to implication slides – done
  • Got all my connections set up
  • Successfully converted and deployed cosmos-2
  • Voted!

Phil 6.20.18

7:00 – 9:00 2:00 – 5:00 ASRC MKT

  • Redo doodle for all of August – done
  • Schooling Fish May Offer Insights Into Networked Neurons
    • Iain Couzin is deciphering the rules that govern group behavior. The results might provide a fresh perspective on how networks of neurons work together.
  • City arts and lectures: The New Science Of Psychedelics With Michael Pollan
    • Psychedelics reduce the section of the brain that have to do with the sense of self. Pollan thinks that this also happens with certain types of rhythmic music and in crowd situations. This could be related to stampedes and flocking.
    • LSD May Chip Away at the Brain’s “Sense of Self” Network
      • Brain imaging suggests LSD’s consciousness-altering traits may work by hindering some brain networks and boosting overall connectivity
  • Add an attractor scalar for agents that’s normally zero. A vector to each agent within the SIH is calculated and scaled by the attractor scalar. That vector is then added to the direction vector to the agent – done?
  • Remove the heading influence based on site – done
  • Add a white circle to the center of the agent that is the size of the attraction scalar. Done
  • Add a ‘site trajectory’ to the spreadsheet that will have the site lists (and their percentage?)
  • Worked on A2P white paper with Aaron.
  • Worked on a response to Dr. Li’s response

ASRC IRAD 9:00 – 2:00

  • Mind meld with Bob
    • Revisit Yarn
    • Excel stuff?
    • Connect to AWS using bastion. Look in FoxyProxy how to. I need certs
    • Drop on rabbit to deploy to CI and QA and NESDIS  ONE (production)
    • Don’t want sensitive information in Git. We use sharepoint instead
    • Notes and screenshots in document.

Phil 6.11.18

7:00 – 6:00 ASRC MKT

  • More Bit by Bit. Reading the section on ethics. It strikes me that simulation could be a way to cut the PII Gordion Knot in some conditions. If a simulation can be developed that generates statistically similar data to the desired population, then the simulated data and the simulation code can be released to the research community. The dataset becomes infinite and adjustable, while the PII data can be held back. Machine learning systems trained on the simulated data can then be evaluated on the confidential data. The differences in the classification by the ML systems between real data and simulated data can also provide insight into the gaps in fidelity of the simulated data, which would provide an ongoing improvement to the simulation, which could in turn be released to the community.
  • Continuing with the cleanup of the SASO paper. Mostly done but some trimming of redundent bits and the “Ose Simple Trick” paragraph.
  • SASO travel link
    • Monday prices: SASO
  • Fika
    • Come up with 3-5 options for a finished state for the dissertation. It probably ranges from “pure theory” through “instance based on theory” to “a map generated by the system that matches the theory”
    • Once the SASO paper is in, set up a “wine and cheese” get together for the committee to go over the current work and discuss changes to the next phase
    • Start on a new IRB. Emphasize how everyone will have the same system to interact with, though their interactions will be different. Emphasize that the system has to allow open interaction to provide the best chance to realize theoretical results.
    • Will and I are on the hook for a Fika about LaTex

Phil 5.15.18

7:00 – 4:00 ASRC MKT

Phil 5.1.18

7:00 – 4:30 ASRC MKT

  • Applications of big social media data analysis: An overview
    • Over the last few years, online communication has moved toward user-driven technologies, such as online social networks (OSNs), blogs, online virtual communities, and online sharing platforms. These social technologies have ushered in a revolution in user-generated data, online global communities, and rich human behavior-related content. Human-generated data and human mobility patterns have become important steps toward developing smart applications in many areas. Understanding human preferences is important to the development of smart applications and services to enable such applications to understand the thoughts and emotions of humans, and then act smartly based on learning from social media data. This paper discusses the role of social media data in comprehending online human data and in consequently different real applications of SM data for smart services are executed.
  • Explainable, Interactive Deep Learning
    • Recently, deep learning has been advancing the state of the art in artificial intelligence to yet another level, and humans are relying more and more on the outputs generated by artificial intelligence techniques than ever before. However, even with such unprecedented advancements, the lack of interpretability on the decisions made by deep learning models and no control over their internal processes act as a major drawback when utilizing them to critical decision-making processes such as precision medicine and law enforcement. In response, efforts are being made to make deep learning interpretable and controllable by humans. In this paper, we review recent studies relevant to this direction and discuss potential challenges and future research directions.
  • Building successful online communities: Evidence-based social design (book review)
    • In Building Successful Online Communities (2012), Robert Kraut, Paul Resnick, and their collaborators set out to draw links between the design of socio-technical systems with findings from social psychology and economics. Along the way, they set out a vision for the role of social sciences in the design of systems like mailing lists, discussion forums, wikis, and social networks, offering a way that behavior on those platforms might inform our understanding of human behavior.
  • Since I’ve forgotten my Angular stuff, reviewing UltimateAngular, Angular Fundamentals course. Finished the ‘Getting Started’ section
  • Strip out Guttenburg text from corpora – done!

Phil 4.30.18

7:00 – 4:30 ASRC MKT

  • Some new papers from ICLR 2018
  • Need to write up a quick post for communicating between Angular and a (PHP) server, with an optional IntelliJ configuration section
  • JuryRoom this morning and then GANs + Agents this afternoon?
  • Next steps for JuryRoom
    • Start up the AngularPro course
    • Set up PHP access to DB, returning JSON objects
  • Starting Agent/GAN project
    • Need to set up an ACM paper to start dumping things into – done.
    • Looking for a good source for Jack London. Gutenberg looks nice, but there is a no-scraping rule, so I guess, we’ll do this by hand…
    • We will need to check for redundant short stories
    • We will need to strip the front and back matter that pertains to project Gutenburg
      • *** START OF THIS PROJECT GUTENBERG EBOOK BROWN WOLF AND OTHER JACK ***
      • *** END OF THIS PROJECT GUTENBERG EBOOK BROWN WOLF AND OTHER JACK ***
  • Fika: Accessibility at the Intersection of Users and Data
    • Nice talk and followup discussion with Dr. Hernisa Kacorri, who’s combining machine learning and HCC
      • My research goal is to build technologies that address real-world problems by integrating data-driven methods and human-computer interaction. I am interested in investigating human needs and challenges that may benefit from advancements in artificial intelligence. My focus is both in building new models to address these challenges and in designing evaluation methodologies that assess their impact. Typically my research involves application of machine learning and analytics research to benefit people with disabilities, especially assistive technologies that model human communication and behavior such as sign language avatars and independent mobility for the blind.

Phil 4.19.18

8:00 – ASRC MKT/BD

    • Good discussion with Aaron about the agents navigating embedding space. This would be a great example of creating “more realistic” data from simulation that bridges the gap between simulation and human data. This becomes the basis for work producing text for inputs such as DHS input streams.
      • Get the embedding space from the Jack London corpora (crawl here)
      • Train a classifier that recognizes JL using the embedding vectors instead of the words. This allows for contextual closeness. Additionally, it might allow a corpus to be trained “at once” as a pattern in the embedding space using CNNs.
      • Train an NN(what type?) to produce sentences that contain words sent by agents that fool the classifier
      • Record the sentences as the trajectories
      • Reconstruct trajectories from the sentences and compare to the input
      • Some thoughts WRT generating Twitter data
        • Closely aligned agents can retweet (alignment measure?)
        • Less closely aligned agents can mention/respond, and also add their tweet
    • Handed off the proposal to Red Team. Still need to rework the Exec Summary. Nope. Doesn’t matter that the current exec summary does not comply with the requirements.
    • A dog with high social influence creates an adorable stampede:
    • Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
      • This is a paper that describes how ML can be used to predict the behavior of chaotic systems. An implication is that this technique could be used for early classification of nomadic/flocking/stampede behavior
    • Visualizing a Thinker’s Life
      • This paper presents a visualization framework that aids readers in understanding and analyzing the contents of medium-sized text collections that are typical for the opus of a single or few authors.We contribute several document-based visualization techniques to facilitate the exploration of the work of the German author Bazon Brock by depicting various aspects of its texts, such as the TextGenetics that shows the structure of the collection along with its chronology. The ConceptCircuit augments the TextGenetics with entities – persons and locations that were crucial to his work. All visualizations are sensitive to a wildcard-based phrase search that allows complex requests towards the author’s work. Further development, as well as expert reviews and discussions with the author Bazon Brock, focused on the assessment and comparison of visualizations based on automatic topic extraction against ones that are based on expert knowledge.