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

‘The Production of Space’, in: Frans Jacobi, Imagine, Space Poetry, Copenhagen, 1996, unpaginated.

The Production of Space

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

This paper introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these partitionings. We first identify several application scenarios for the resultant 'knowledge reuse' framework that we call cluster ensembles. The cluster ensemble problem is then formalized as a combinatorial optimization problem in terms of shared mutual information. In addition to a direct maximization approach, we propose three effective and efficient techniques for obtaining high-quality combiners (consensus functions). The first combiner induces a similarity measure from the partitionings and then reclusters the objects. The second combiner is based on hypergraph partitioning. The third one collapses groups of clusters into meta-clusters which then compete for each object to determine the combined clustering. Due to the low computational costs of our techniques, it is quite feasible to use a supra-consensus function that evaluates all three approaches against the objective function and picks the best solution for a given situation. We evaluate the effectiveness of cluster ensembles in three qualitatively different application scenarios: (i) where the original clusters were formed based on non-identical sets of features, (ii) where the original clustering algorithms worked on non-identical sets of objects, and (iii) where a common data-set is used and the main purpose of combining multiple clusterings is to improve the quality and robustness of the solution. Promising results are obtained in all three situations for synthetic as well as real data-sets.

/pdf/cluster-ensembles-a-knowledge-reuse-framework-for-combining-3qjcysq4q0.pdf

Cluster ensembles --- a knowledge reuse framework for combining multiple partitions

Meanwhile, the authors' antidote to the American sicknessa quest for democratic community that draws on our diverse civic and religious traditionshas contributed to a vigorous scholarly and popular debate. Attention has been focused on forms of social organization, be it civil society, democratic communitarianism, or associative democracy, that can humanize the market and the administrative state. In their new Introduction the authors relate the argument of their book both to the current realities of American society and to the growing debate about the country's future. With this new edition one of the most influential books of recent times takes on a new immediacy.\

Habits of the Heart: Individualism and Commitment in American Life

Lifelong Machine Learning, or LML, considers systems that can learn many tasks from one or more domains over its lifetime. The goal is to sequentially retain learned knowledge and to selectively transfer that knowledge when learning a new task so as to develop more accurate hypotheses or policies. Following a review of prior work on LML, we propose that it is now appropriate for the AI community to move beyond learning algorithms to more seriously consider the nature of systems that are capable of learning over a lifetime. Reasons for our position are presented and potential counter-arguments are discussed. The remainder of the paper contributes by defining LML, presenting a reference framework that considers all forms of machine learning, and listing several key challenges for and benefits from LML research. We conclude with ideas for next steps to advance the field.

/pdf/lifelong-machine-learning-systems-beyond-learning-algorithms-4j01370oid.pdf

Lifelong Machine Learning Systems: Beyond Learning Algorithms

The goal of neural-symbolic computation is to integrate robust connectionist learning and sound symbolic reasoning. With the recent advances in connectionist learning, in particular deep neural networks, forms of representation learning have emerged. However, such representations have not become useful for reasoning. Results from neural-symbolic computation have shown to offer powerful alternatives for knowledge representation, learning and reasoning in neural computation. This paper recalls the main contributions and discusses key challenges for neural-symbolic integration which have been identified at a recent Dagstuhl seminar.

/pdf/neural-symbolic-learning-and-reasoning-contributions-and-3kcf44ooa9.pdf

Neural-Symbolic Learning and Reasoning: Contributions and Challenges

The task rehearsal method (TRM) is introduced as an approach to life-long learning that uses the representation of previously learned tasks as a source of inductive bias. This inductive bias enables TRM to generate more accurate hypotheses for new tasks that have small sets of training examples. TRM has a knowledge retention phase during which the neural network representation of a successfully learned task is stored in a domain knowledge database, and a knowledge recall and learning phase during which virtual examples of stored tasks are generated from the domain knowledge. The virtual examples are rehearsed as secondary tasks in parallel with the learning of a new (primary) task using the ?MTL neural network algorithm, a variant of multiple task learning (MTL). The results of experiments on three domains show that TRM is effective in retaining task knowledge in a representational form and transferring that knowledge in the form of virtual examples. TRM with ?MTL is shown to develop more accurate hypotheses for tasks that suffer from impoverished training sets.

The Task Rehearsal Method of Life-Long Learning: Overcoming Impoverished Data

This article builds on an important but underdeveloped social science concept—the "scene" as a cluster of urban amenities—to contribute to social science theory and subspecialties such as urban and rural, class, race and gender studies Scenes grow more important in less industrial, more expressively-oriented and contingent societies where traditional constraints fall and self-motivated action around consumption, leisure and amenities is a more important feature of social cohesiveness and interaction Scenes contextualize the individual through amenities and consumption-based expressions of shared sensibilities as to what is right, beautiful and genuine This framework adds to concepts such as neighborhood and workplace by specifying 15 dimensions of the urban scenescape Like neighborhood and workplace, scenes reduce anomie, but because of their focus on consumption and the use of specific amenities, they are more consistent with today's ethos of contingency, moving beyond traditional ideas of the fundamental power of social, family and occupational background We introduce a new amenities-focused database to measure and analyze scenes and their dimensions for each of 40,000 US zip codes We illustrate the framework by applying it to one distinct type of scene, bohemia, and analyze its position in the broader social system

Scenes: Social Context in an Age of Contingency

With a distinction made between two forms of task knowledge transfer, 'representational' and 'functional', eta MTL, a modified version of the multiple task learning (MTL) method of functional (parallel) transfer, is introduced. The eta MTL method employs a separate learning rate, etak, for each task output node k. etak varies as a function of a measure of relatedness, Rk, between the kth task and the primary task of interest. Results of experiments demonstrate the ability of eta MTL to dynamically select the most related source task(s) for the functional transfer of prior domain knowledge. The eta MTL method of learning is nearly equivalent to standard MTL when all parallel tasks are sufficiently related to the primary task, and is similar to single task learning when none of the parallel tasks are related to the primary task.

Daniel Silver

Papers

Lifelong Machine Learning Systems: Beyond Learning Algorithms

Neural-Symbolic Learning and Reasoning: Contributions and Challenges

The Task Rehearsal Method of Life-Long Learning: Overcoming Impoverished Data

Scenes: Social Context in an Age of Contingency

The Parallel Transfer of Task Knowledge Using Dynamic Learning Rates Based on a Measure of Relatedness