Basics of qualitative research: Grounded theory procedures and techniques

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

How to Do Things With Words

From the Publisher: 
A Question of Identity 
Life on the Screen is a fascinating and wide-ranging investigation of the impact of computers and networking on society, peoples' perceptions of themselves, and the individual's relationship to machines. Sherry Turkle, a Professor of the Sociology of Science at MIT and a licensed psychologist, uses Internet MUDs (multi-user domains, or in older gaming parlance multi-user dungeons) as a launching pad for explorations of software design, user interfaces, simulation, artificial intelligence, artificial life, agents, "bots," virtual reality, and "the on-line way of life." 
Turkle's discussion of postmodernism is particularly enlightening. She shows how postmodern concepts in art, architecture, and ethics are related to concrete topics much closer to home, for example AI research (Minsky's "Society of Mind") and even MUDs (exemplified by students with X-window terminals who are doing homework in one window and simultaneously playing out several different roles in the same MUD in other windows). Those of you who have (like me) been turned off by the shallow, pretentious, meaningless paintings and sculptures that litter our museums of modern art may have a different perspective after hearing what Turkle has to say. 
This is a psychoanalytical book, not a technical one. However, software developers and engineers will find it highly accessible because of the depth of the author's technical understanding and credibility. Unlike most other authors in this genre, Turkle does not constantly jar the technically-literate reader with blatant errors or bogus assertions about how things work. Although I personally don't have time or patience for MUDs,view most of AI as snake-oil, and abhor postmodern architecture, I thought the time spent reading this book was an extremely good investment.

스크린 위의 삶 = Life on the screen : identity in the age of the internet

Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an important challenge for artificial intelligence research, owing to its iconic and enduring status among the most difficult professional esports and its relevance to the real world in terms of its raw complexity and multi-agent challenges. Over the course of a decade and numerous competitions1-3, the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems4. Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general-purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks5,6. We evaluated our agent, AlphaStar, in the full game of StarCraft II, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8% of officially ranked human players.

Grandmaster level in StarCraft II using multi-agent reinforcement learning.

Contemporary games are making significant strides towards offering complex, immersive experiences for players. We can now explore sprawling 3D virtual environments populated by beautifully rendered characters and objects with autonomous behavior, engage in highly visceral action-oriented experiences offering a variety of missions with multiple solutions, and interact in ever-expanding online worlds teeming with physically customizable player avatars.

https://www.cc.gatech.edu/~isbell/reading/papers/MateasSternGDC03.pdf

Façade: An Experiment in Building a Fully-Realized Interactive Drama

Information visualization has often focused on providing deep insight for expert user populations and on techniques for amplifying cognition through complicated interactive visual models. This paper proposes a new subdomain for infovis research that complements the focus on analytic tasks and expert use. Instead of work-related and analytically driven infovis, we propose casual information visualization (or casual infovis) as a complement to more traditional infovis domains. Traditional infovis systems, techniques, and methods do not easily lend themselves to the broad range of user populations, from expert to novices, or from work tasks to more everyday situations. We propose definitions, perspectives, and research directions for further investigations of this emerging subfield. These perspectives build from ambient information visualization (Skog et al., 2003), social visualization, and also from artistic work that visualizes information (Viegas and Wattenberg, 2007). We seek to provide a perspective on infovis that integrates these research agendas under a coherent vocabulary and framework for design. We enumerate the following contributions. First, we demonstrate how blurry the boundary of infovis is by examining systems that exhibit many of the putative properties of infovis systems, but perhaps would not be considered so. Second, we explore the notion of insight and how, instead of a monolithic definition of insight, there may be multiple types, each with particular characteristics. Third, we discuss design challenges for systems intended for casual audiences. Finally we conclude with challenges for system evaluation in this emerging subfield.

/pdf/casual-information-visualization-depictions-of-data-in-2vyoflmjx0.pdf

Casual Information Visualization: Depictions of Data in Everyday Life

We present a data mining approach to opponent modeling in strategy games. Expert gameplay is learned by applying machine learning techniques to large collections of game logs. This approach enables domain independent algorithms to acquire domain knowledge and perform opponent modeling. Machine learning algorithms are applied to the task of detecting an opponent's strategy before it is executed and predicting when an opponent will perform strategic actions. Our approach involves encoding game logs as a feature vector representation, where each feature describes when a unit or building type is first produced. We compare our representation to a state lattice representation in perfect and imperfect information environments and the results show that our representation has higher predictive capabilities and is more tolerant of noise. We also discuss how to incorporate our data mining approach into a full game playing agent.

A data mining approach to strategy prediction

A behavior language is a reactive planning language, based on the Oz Project language Hap, designed specifically for authoring believable agents-characters that express rich personality, and that, in this case, play roles in an interactive story called Facade.

/pdf/a-behavior-language-for-story-based-believable-agents-4iis11ya78.pdf

A behavior language for story-based believable agents

The process of building Facade, a first-person, real-time, one-act interactive drama, has involved three major research efforts: designing ways to deconstruct a dramatic narrative into a hierarchy of story and behavior pieces; engineering an AI system that responds to and integrates the player's moment-by-moment interactions to reconstruct a real-time dramatic performance from those pieces; and understanding how to write an engaging, compelling story within this new organizational framework. This paper provides an overview of the process of bringing our interactive drama to life as a coherent, engaging, high agency experience, including the design and programming of thousands of joint dialog behaviors in the reactive planning language ABL, and their higher level organization into a collection of story beats sequenced by a drama manager. The process of iteratively developing the architecture, its languages, authorial idioms, and varieties of story content structures are described. These content structures are designed to intermix to offer players a high degree of responsiveness and narrative agency. We conclude with design and implementation lessons learned and future directions for creating more generative architectures.

/pdf/structuring-content-in-the-facade-interactive-drama-2ig9556gsz.pdf

Michael Mateas

Papers

Façade: An Experiment in Building a Fully-Realized Interactive Drama

Casual Information Visualization: Depictions of Data in Everyday Life

A data mining approach to strategy prediction

A behavior language for story-based believable agents

Structuring content in the Façade interactive drama architecture