Bayes' Theorem in Technology

by Dax Bradley

The Bayesian model for statistical analysis is highly popular in settings that require predictive strength to succeed.  Industries are numerous, from academic areas such as astronomy, to industrial applications to include telecommunications and pharmaceutical companies (May, 2014).  In the telecom sector, the method has been employed for some time.  Akamai Technologies in Cambridge uses Bayesian methods to better understand network latencies, internet traffic, and to identify clusters of users (Galkowski, 2014).

The computational complexity of the Bayesian model would suggest that primarily technology-based efforts would embrace this form of analysis (Edelsbrunner, 2014).  Google’s robotic cars, and Microsoft’s own early spam filters stood on the strength of Bayes theorem (McGrayne, 2011).  Google’s strength lies not only in the high level of technical prowess, which is obvious, but also by a factor not apparent: the large amount of data to draw from.

The Bayes approach relies heavily on what is known already to make a successful prediction on what is likely to happen (Russell & Norvig, 2010).  Google translate uses Bayes Theorem in the translation services, by drawing on a large pool of translation data already completed by humans (King, 2015).  So, rather than undergoing large amounts of translation algorithms, the software instead draws from experience, samples the data, and predicts the highest certainty.  The method has been applied by Google not only in translation and mapping, but also in controlling driverless cars. 

The tech giant claims that their autonomous vehicles have logged as many as 140,000 miles along the Pacific Coastal highway, all without incident (Matyszczyk, 2011).

It is easy to see how Bayesian methods are highly prized in the technology sector.  The approach is also critical in health technology assessment.  While no formal definition of Bayesian tools in healthcare technology has been established, proponents believe that it provides for conclusions in a form most appropriate for decisions specific to patients and decisions affecting policy.  That is based upon the following conclusions (Spiegelhalter, Myles, & Jones, 1999, para. 4):

• Data are interpreted from a study in the light of external evidence and judgement
• The form in which conclusions are drawn naturally contributes to decisions
• Prior plausibility of hypotheses is taken into account
• Skepticism about large treatment effects are formally expressed and cautiously interpreted
• Use of Bayesian methods in healthcare technology assessment are to be pursued carefully; guidelines, software, and critically evaluated case studies are needed

References

Edelsbrunner, P. (2014, November 17). Bayesian statistics: What is it and why do we need it? [Blog post]. Retrieved from JEPS Bulletin: http://blog.efpsa.org/2014/11/17/bayesian-statistics-what-is-it-and-why-do-we-need-it-2/

Galkowski, J. (2014, October 17). How companies use Bayesian methods [Online forum comment]. Retrieved from http://andrewgelman.com/2014/10/17/companies-use-bayesian-methods/

King, M. (2015, July 20). Bayes’ theorem and what we do [Blog post]. Retrieved from https://www.whitehatsec.com/blog/bayes-theorem-and-what-we-do/

Matyszczyk, C. (2011, March 4). Google’s self-driving car goes all Dale Earnhardt. Cnet. Retrieved from https://www.cnet.com/news/googles-self-driving-car-goes-all-dale-earnhardt/

May, J. (2014, October 17). How do companies use Bayesian methods? [Online forum comment]. Retrieved from http://andrewgelman.com/2014/10/17/companies-use-bayesian-methods/

McGrayne, S. (2011). Why Bayes rules: The history of a formula that drives modern life. Retrieved January 19, 2017, from https://www.scientificamerican.com/article/why-bayes-rules/

Russell, S., & Norvig, P. (2010). Artificial Intelligence: A modern approach (3rd ed.). Boston, MA: Pearson.

Spiegelhalter, D., Myles, J., & Jones, D. (1999, August 21). An introduction to bayesian methods in health technology assessment. The BMJ, 319(1), 7208. Retrieved from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1116393/

Bayesian Model Challenges

By Dax Bradley

Possible disadvantages to Bayesian learning methods can be significant.  For one thing, the information gleaned from the effort could be theoretically infeasible.  The act of specifying a prior datum is challenging.  Generally, it is necessary to specify a real number for every setting in the real-world parameters (Langford, 2005).  One potential solution is to acquire languages that allow more compact specification of priors.  The task of learning a new language may be prohibitive.  Another solution is to simply lie.  In other words, create a specification that is not accurate.  As deceitful as this sounds, it is not meant that way; in fact, it has been shown to be effective (Langford, 2005).

Another known disadvantage to Bayesian modeling lies in the analysis of causality.  There is a great challenge in analyzing the conditional probability links between various nodes.  Even with physical causal models and known variables, the computational burden is great, since the task equates to inverting a finite-element model (Sankararaman, 2015).  This is especially daunting if the analysis revolves around an acyclic model.  The assumption of independence among variables implies no latent cofounding variable in Bayesian modeling; however, often there are acyclic latent cofounding variables which can force the model to be seriously biased (Shimizu & Bollen, 2014).

Prior choice problems present challenges in the Bayesian methodology.  Another scenario in which researchers using the model is in astronomy.  Scientists have attempted to predict the number of extra-solar planets in this way.  Improper priors are generally disallowed here, so other strategies have been suggested, such as Intrinsic Bayes, Fractional Bayes, and Expected posterior factors (Jeffreys, 2006, p. 11).  The potential defeat of using such methods is that data may be inadvertently duplicated, so allowances must be made.

Many forms of industry employ the Bayesian model of statistical probability.  In drug development, the approach is widely regarded for its accuracy and natural interpretation.  It does, however, demand no small degree of planning.  The flexibility of this method creates an environment prone to potential computational errors.  Without proper planning, the various outcomes of intense computation may be unreliable, prompting some teams to opt instead for a frequentist model (Gupta, 2012).

References

Gupta, S. (2012, June). Use of Bayesian statistics in drug development: Advantages and challenges. International Journal of Applied & Basic Medical Research, 2(1), 3-6. http://dx.doi.org/Use of Bayesian statistics in drug development: Advantages and challenges

Jeffreys, W. (2006). Current challenges in Bayesian model choice: Comments [Lecture notes]. Retrieved from Department of Statistics University of Vermont: http://astrostatistics.psu.edu/scma4/Jefferys.pdf

Langford, J. (2005, April 23). Advantages and disadvantages to Bayesian learning [Discussion group comment]. Retrieved from http://hunch.net/?p=65
Sankararaman, S. (2015). What are the limitations of Bayesian Networks? Retrieved January 18, 2017, from https://www.quora.com/What-are-the-limitations-of-Bayesian-Networks

Shimizu, S., & Bollen, K. (2014, August). Bayesian Estimation of Causal Direction in Acyclic Structural Equation models with individual-specific confounder variables and non-Gaussian distributions. Journal of Machine Learning Research, 15(1), 2629-2652. Retrieved from http://jmlr.org/papers/volume15/shimizu14a/shimizu14a.pdf

Bayesian Theorem - Advantages

by Dax Bradley

Creating complex models from complex data can prove to be an arduous task, even in a system of computers.  Using even existing data, a computing system must perform many calculations, often at the expense of vast resources.  It can be difficult to express a problem mathematically, particularly using highly details models available through direct or indirect complex mechanisms.  It would be no small challenge for a computing tool to interpolate shapes and behavior from raw video footage, providing a prohibitively large amount of variability and noise (Hertzmann, 2004, p. 5).

Bayesian reasoning provides a methodology for many data-modeling problems.  By searching for logic in uncertainty, Bayesian methods provide a unified approach that on the surface is like human logic.  Bayesian logic provides three main areas of interest:

1. Principled modeling of uncertainty

2. General purpose models for unstructured data

3. Effective algorithms for data fitting and analysis under uncertainty

Courtesy: CBS

There are advantages to Bayes learning method.  One area is in interpolation.  When faced with a challenge in engineering, there is always a balancing act to determine whether the time and resources a human would consume vs. a computing system.  With the formulation of an engineering system, a world model must be built, along with a “controller” for that environment.  Bayesian methods interpolate this to the extreme because the Bayesian prior can be a delta function on one model of the world (Barak, 2005).

The Bayesian method also obeys the likelihood principle.  In a case where two proportional likelihood functions come from two distinct samples for , then all inferences about both groups will be similar (Jones & Huddleson, 2015).  It also provides interpretable answers in a convenient setting for a wide range of models.  This includes hierarchical models as well as missing-data problems.  Less training data is also required; in fact, lower training data is preferred with the Bayes naïve approach (Chen,  2011, para. 3).  A naïve Bayes classifier will converge more efficiently than discriminative models such as logistic regression.

References

Barak, B. (2005). Advantages and disadvantages of Bayesian learning. Retrieved January 17, 2017, from http://hunch.net/?p=65

Chen, E. ( 2011, April 27). Choosing a machine learning classifier [Blog post]. Retrieved from http://blog.echen.me/2011/04/27/choosing-a-machine-learning-classifier

Hertzmann, A. (2004). Introduction to Bayesian learning [Lecture notes]. Retrieved from https://www.dgp.toronto.edu/~hertzman/ibl2004/notes.pdf

Jones, A., & Huddleson, E. (2015). Bayesian analysis: Advantages and disadvantages. Retrieved January 17, 2017, from https://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#statug_introbayes_sect006.htm

Bots for Gaming and Ethical Questions

by Dax Bradley

For the most part, the discussion of bots in gaming revolves around those that fall within uses of morally and legally acceptable standards. Bots and macros that are widely regarded as legal appear to be distinguished by the factor of a human operator being present. However, the question persists as to what happens if an intrepid programmer creates a bot capable of playing an online game. This topic is a hot-button issue in the gaming community, and partly rests about intent. A player may program a bot to carry out commands in sequence for the game’s avatar. For example, suppose a player in a game can score a large amount of points by attacking an enemy with a hack-slash-slash-jump back sequence, but the keyboard commands are complex and difficult to execute. A bot could be created to carry out the keyboard combination automatically if the user simply presses ALT-1.

One argument for this scenario is that the bot is merely an extension of the player. The human must be present to initiate the command, and is thus not fully relying on an AI tool to play for him. However, users can (and already have) created routines that fully control a character’s actions, including searching an environment, taking up resources and “killing off” other players to win the game. This brings to the front a concern in the gaming community. A player in one forum expresses it in this way (User Aceboy1993, 2015, June 23):

“This question has been on my mind for a while...mainly because I see bots for all sorts of games like WoW and others. My question is; how do the bots know what is appearing on the screen? I don't play WoW so my example may be wrong but if for example there is a monster, how does the bot know where that monster is on the screen and how does it know how to interact with it?Can you apply this to any game or is it specific for each game? I'm sorry if the question isn't clear...and I'm not asking how to make a bot, more asking how they detect things on the screen as its quite fascinating to me! Thanks in advance :)”

The question also points out an interesting angle: the applications are available that play the games such as the above-mentioned World of Warcraft, but how? How do they perceive the environment well enough to interact? One answer is the software Netshark, which reads encrypted net code and “announces” loot to the bot, triggering whatever actions are wanted to acquire the loot (Nilly, 2013). Besides gobbling up the loot and other rewards, bots have created a dilemma for online gamers by clogging up networks with drones, creating trouble for humans who pay monthly fees for the gaming service.

Game developer Blizzard responded to bots on their World of Warcraft server by aggressively flagging and banning suspected bots, resulting in the removal of over 100,000 accounts (Grayson, 2015). Bot makers have responded by coming up with tools to avoid being flagged, ranging from highly complex algorithms to simple techniques. One such project, RsBot, manages to copy the contents of the game client to its own memory, check the state locally, and make decisions there without risk of detection (Kaslai, 2015).

Another reason bot makers draw the ire of game makers is in how they profit off of a game they had no hand in developing. Developer Josh Phillips of Kapersky Lab, claims to have sold 100,000 copies of his creation, which gives users invulnerability in online games (David, 2012). The industry has even taken a bite out of online gambling. Ray Bornert developed an AI program capable of counting cards on an online Poker site, allowing users to play Poker and Blackjack with the precision of a computer (Kushner, 2005). Gambling sites have caught on to the nonhuman players, however, and responded by including a chat feature, allowing players to chat in a sidebar. The feature has been used successfully to flush out bots incapable of human conversation.

References

Aceboy1993. (2015, June 23). Bots in WoW. [Discussion forum]. Retrieved January 4, 2017 from https://github.com/PokemonGoF/PokemonGo-Bot/issues/2578

David, B. (2012). Hacking online games: Josh Phillips and Michael Donnelly at Defcon 19. Retrieved January 4, 2017 from http://privacy-pc.com/news/hacking-online-games-josh-phillips-and-michael-donnelly.html

Grayson, N. (2015). World of Warcraft bot maker calls it quits after massive ban wave. Retrieved January 4, 2017 from http://kotaku.com/world-of-warcraft-bot-maker-calls-it-quits-after-massiv-1704809117

Kaslai. (2015). How do gamebots perceive the game world & other entities? [Discussion forum]. Retrieved January 4, 2017 from http://gamedev.stackexchange.com/questions/102849/how-do-game-bots-perceive-the-game-world-other-entities/102853

Kushner, D. (2005, September 1). On the internet, nobody knows you are a bot. Wired.

Nilly. (2015). How to read packet data using Wireshark? [Discussion forum]. Retrieved January 4, 2017 from http://www.mpgh.net/forum/showthread.php?t=700530

Bots and AI

The legality of using bots in programming is a grey area presently. While it is open to some legal interpretation, it is generally accepted that bots used to save time on a task that is 100% in control of a human is perfectly reasonable. Used as an advanced macro, a bot can make a complex task more efficient, saving time. The most basic example is a simple mouse and keyboard recorder application. Essentially, the user would load the application, and then allow it to record whatever actions are needed to achieve the desired result. Ideally, the goal is to begin at the home screen, record the action, and return to the same screen in order to make the sequence loopable.

The ideal bot recorder includes an editor to facilitate custom scripts (Zhang, 2016). One such application is Auto Hotkey, and is unique among other script programs as it requires some coding knowledge. The tradeoff is that besides being a simple recorder, it is customizable. Users have shared scripts to perform such tasks as instantly turning off a PC monitor, changing the function of the accent key above the TAB to a backspace, or even automatically clean up an email account on a daily basis (Glenn, 2013). Bots and other recorders are highly useful in making mundane tasks more efficient. There are certain pitfalls to avoid when using macro recorders, however.

A dedicated PC is highly recommended for customized scripts. If any settings are different, such as window size or resolution, the results will likely be undesirable (McCreath, 2016). Open source tools such as Slash allow users to write custom bots capable of performing an almost limitless number of mundane tasks, such as following a GPS tracking web site and instructing the bot to report back coordinates to the user at regular intervals (Haughley, 2015). Bots of this variety are examples of basic artificial intelligence programs designed to mimic human responses, and are widely used by troubleshooting sites and other businesses.

Bots that are legal are also built into established services, as an optional feature. Customizable news and notifications are available that can report content as soon as it becomes available via products like Forbes Bot, and Tech Crunch Bot (Bridgewater, 2016, November 22). Chat bots assist travel companies to help consumers narrow down their travel needs in an automated process, eliminating the need to pore through thousands of options. Similarly, news agencies use bots to help users consolidate their consumption, citing how readers don’t like to load multiple apps. Readers on average have only one or two news apps installed on their devices (Upbin, 2016).

References

Bridgewater, A. (2016, November 22). Come fly with AI, IBM cloud builds ‘chatbot’ virtual travel agent. Forbes. Retrieved January 4, 2017 from http://www.forbes.com/sites/adrianbridgwater/2016/11/22/come-fly-with-ai-ibm-cloud-builds-chatbot-virtual-travel-agent/#5ceb7d671f39+

Glenn, W. (2013). Show us your best Autohotkey script. Retrieved January 4, 2017 from http://lifehacker.com/show-us-your-best-autohotkey-script-507227185

Haughley, M. (2015). A beginner’s guide to your first bot. Retrieved January 4, 2017 from https://slackhq.com/a-beginner-s-guide-to-your-first-bot-97e5b0b7843d#.nvclmr6pb

McCreath, D. (2016). Your first custom slash command for Slack. Retrieved January 4, 2017 from https://github.com/mccreath/isitup-for-slack/blob/master/docs/TUTORIAL.md

Upbin, B. (2016). Introducing the Forbes newsbot on Telegram. Retrieved January 4, 2017 from http://www.forbes.com/sites/bruceupbin/2016/02/23/introducing-the-forbes-newsbot-on-telegram/#64b8ee03117c

Zhang, G. (2016). 8 free macro recorder that automate your traditional mouse and keyboard. Prohavit. Retrieved January 4, 2017 from https://www.prohavit.com/blog/8-free-macro-recorder-automate-traditional-mouse-keyboard/

Bots!

The advancement of artificial intelligence has fostered many tools designed to both mimic human behavior and make mundane tasks easier. One area which has seen an explosion of innovation in online interaction is the development of “bots”. Put simply, bots are applications designed to respond within another program to automatically achieve some result. They come in a variety of styles. There are telegram bots, game bots, and telegram bots, to name a few. Each bot performs unique functions. For example, telegram bots autonomously answer inline queries in HTML5-based games (Martin, 2016, October 17).

Using the software available through a company called The Botfather, users are able to automatically follow a game’s lifecycle through the following process:
1.The user requests a game through the /play prompt
2.A sendgame function is remotely sent in response by the API setting the buttons
3.The user taps the play solo button, and the game bot responds by sending the game’s URL and sets parameters
4.When the player scores in the game a setScore function is established in the cache

The tool in the above example allows players to remotely handle many games and gather resources, points, and other rewards. The performance of bots is based on a machine-state flow process. Bots are designed to “read” the screen (pixels, text, packets or memory) to discover the state, and then respond per the programming (Mai, 2009). This is where the key distinction between bots and macros lies. A macro has been defined on Tech Target in terms of programming as (Griffen & Lowery, 2015):

“…in Microsoft Word and other programs, a macro is a saved sequence of commands or keyboard strokes that can be stored and then recalled with a single command or keyboard stroke.”

In other words, a macro performs when it is instructed to do so by a human. It is merely a shortcut command designed as a time-saver. A bot takes the concept to the next step; performing autonomously. In games and other online applications, it uses artificial intelligence to read a state and respond. Still, users tend to use the terms interchangeably. In C++ programming, developers have devised a method for automating a basic process such as a send key.

Effectively, developing a macro (or bot as many programmers will call it) allows the user to send a virtual key, defined in winuser.h as VK_XXX and a flag noting whether the key is up or down to express whether the virtual key is expressed. The ALT-TAB sequence could be set up in this manner (Bachaalany, 2004):

//press down Alt-Tab
Keybd_event (VK_MENU, 0, 0, 0);
Keybd_event (VK_TAB, 0, 0, 0);
::Sleep (1000);
//stop pressing Alt-Tab
Keybd_event
(VK_MENU, 0, KEYEVENTF_KEYUP, 0);
Keybd_event
(VK_TAB, 0, KEYEVENTF_KEYUP, 0);

As shown above, the event requires four lines of code. The mac o simplifies the process through simply calling a library: #include “Sendkeys.h”

References

Bachaalany, E. (2004). How to do ‘send’ keys in C++. Retrieved January 3, 2017 from https://www.codeproject.com/kb/cpp/sendkeys_cpp_article.aspx

Griffen, T. & Lowery, P. (2005). Definit-ion: Macro. Techtarget. Retrieved January 4, 2017 from http://whatis.techtarget.com/definition/macro

Mai, S. (2009). 10 tips for writing game bots. [Bog post]. Krypted. Retrieved January 2, 2017 from http://krypted.com/sites/5-rules-for-writing-bots-in-games/

Martin, A. (2016, October 17). How to create a game bot and publish your html5 games on Telegram. [Blog post]. Retrieved January 2, 2017 from https://blog.ludei.com/how-to-create-a-game-bot-and-publish-your-html5-games-on-telegram/