• Study Resource
  • Explore
    • Arts & Humanities
    • Business
    • Engineering & Technology
    • Foreign Language
    • History
    • Math
    • Science
    • Social Science

    Top subcategories

    • Advanced Math
    • Algebra
    • Basic Math
    • Calculus
    • Geometry
    • Linear Algebra
    • Pre-Algebra
    • Pre-Calculus
    • Statistics And Probability
    • Trigonometry
    • other →

    Top subcategories

    • Astronomy
    • Astrophysics
    • Biology
    • Chemistry
    • Earth Science
    • Environmental Science
    • Health Science
    • Physics
    • other →

    Top subcategories

    • Anthropology
    • Law
    • Political Science
    • Psychology
    • Sociology
    • other →

    Top subcategories

    • Accounting
    • Economics
    • Finance
    • Management
    • other →

    Top subcategories

    • Aerospace Engineering
    • Bioengineering
    • Chemical Engineering
    • Civil Engineering
    • Computer Science
    • Electrical Engineering
    • Industrial Engineering
    • Mechanical Engineering
    • Web Design
    • other →

    Top subcategories

    • Architecture
    • Communications
    • English
    • Gender Studies
    • Music
    • Performing Arts
    • Philosophy
    • Religious Studies
    • Writing
    • other →

    Top subcategories

    • Ancient History
    • European History
    • US History
    • World History
    • other →

    Top subcategories

    • Croatian
    • Czech
    • Finnish
    • Greek
    • Hindi
    • Japanese
    • Korean
    • Persian
    • Swedish
    • Turkish
    • other →
 
Profile Documents Logout
Upload
The role of artificial intelligence techniques in training
The role of artificial intelligence techniques in training

... 1. The major contribution of AI to educational and training software is the possibility to model expertise. This expertise is the main feature of AI-based courseware: the system is able to solve the problems that the learner has to solve. The system is knowledgeable in the domain to be taught. Of c ...
Learning Strengthens the Response of Primary Visual Cortex to
Learning Strengthens the Response of Primary Visual Cortex to

... that span both stimuli, spatial blurring of the hemodynamic response, noise in the localizer scan, or eye movements during scanning. For example, subjects may have occasionally fixated the middle location, thus moving it to the central location. The reduction in secondary response with learning was ...
Artificial Intelligence: From Programs to Solvers
Artificial Intelligence: From Programs to Solvers

... domain X, such as story understanding, humor, scientific discovery, or circuit analysis, analyzing then how the task is done by humans either by introspection or by interviewing an expert, and capturing this reasoning in a computer program [45,52]. The work was a theory about X along with a program ...
Acta polytechnica Hungarica - Volume 4, Issue No. 1 (2007.)
Acta polytechnica Hungarica - Volume 4, Issue No. 1 (2007.)

... developers to take the system's context into account through the set of defined variables that are linked to the application domain. With these extensions the focus in decision support systems development shifts from task ontology towards domain ontology. Most AI systems operate on a first-principle ...
Case-based Reasoning in Agent-based Decision Support System
Case-based Reasoning in Agent-based Decision Support System

... developers to take the system's context into account through the set of defined variables that are linked to the application domain. With these extensions the focus in decision support systems development shifts from task ontology towards domain ontology. Most AI systems operate on a first-principle ...
Separate-and-Conquer Rule Learning
Separate-and-Conquer Rule Learning

... rules starts with a rule whose body is always true. As long as its still covers negative examples the current rule is specialized by adding conditions to its body. Possible conditions are tests on the presence of certain values of various attributes. In order to move towards the goal of finding a ru ...
Document
Document

... than Statistics and Data Mining? Broadly speaking ML, DM, and Statistics have similar goals (modeling for classification and hypothesis generation or testing). Statistics has traditionally emphasized models that can be solved analytically (for example various versions of the Generalized Linear Model ...
Approaches to Artificial Intelligence
Approaches to Artificial Intelligence

... each others' points of view and the relationships among them. In this report, we will present abstracts of all of the presentations (written by their authors after the workshop) and summaries of the discussions that took place at the workshop (written from rough notes). It seems to us that the sever ...
Closed-Form Learning of Markov Networks from Dependency
Closed-Form Learning of Markov Networks from Dependency

... of each variable given its Markov blanket, it is easily applied to DNs. The probability distribution represented by a DN is defined as the stationary distribution of the Gibbs sampler, given a fixed variable order. If the DN is consistent, then its conditional distributions must be consistent with s ...
Document
Document

... 'Deep learning' is a set of algorithms in machine learning that attempt to learn in multiple levels of representation, corresponding to different levels of abstraction. It typically uses artificial neural networks. The levels in these learned statistical models correspond to distinct levels of conce ...
Learning logical definitions from relations
Learning logical definitions from relations

... Concept learning, which Hunt, Marin, and Stone (1966) describe succinctly as "[the] capacity to develop classification rules from experience" has long been a principal area of machine learning research. Supervised concept learning systems are supplied with information about several entities whose cl ...
A Foundational Architecture for Artificial General Intelligence
A Foundational Architecture for Artificial General Intelligence

... AGI. I know you’ll think this won’t sound anything like AGI. It’s far from general intelligence, but in my view this is where we have to start. This simple ontology will lead us to the beginnings of a foundational architecture for AGI. ...
Sources of Evidence-of-Learning: Learning and assessment in the
Sources of Evidence-of-Learning: Learning and assessment in the

... 4498 studies and involving four million students, John Hattie concludes that ‘there is no necessary relation between having computers, using computers and learning outcomes’. Nor are there changes over time in overall effect sizes, notwithstanding the increasing sophistication of computer technologi ...
Quo vadis, computational intelligence?
Quo vadis, computational intelligence?

... (virtual networks) should be used. More complex internal knowledge and interaction patterns of PEs are worth investigation. The simplest extension of network processing elements that adds more internal parameters requires abandoning the sigmoidal neurons and using a more complex transfer functions. ...
Quo vadis, computational intelligence
Quo vadis, computational intelligence

... and hybrid systems. In our opinion it should be used to cover all branches of science and engineering that are concerned with understanding and implementing functions for which effective algorithms do not exist. From this point of view some areas of AI and a good part of pattern recognition, image a ...
Curriculum Vitae - People.csail.mit.edu
Curriculum Vitae - People.csail.mit.edu

... With advisor Leslie Pack Kaelbling, developing a modern cognitive architecture. The driving application in mind is to develop software-based secretaries that understand their bosses’ habits and can carry out their wishes automatically. Research Assistant, Institute for Computer Science, Albert-Ludwi ...
WAIC AND WBIC ARE INFORMATION CRITERIA FOR SINGULAR
WAIC AND WBIC ARE INFORMATION CRITERIA FOR SINGULAR

... Many statistical models and learning machines which have hierarchical structures, hidden variables, and grammatical rules are not regular but singular statistical models. In singular models, the log likelihood function can not be approximated by any quadratic form of a parameter, resulting that conv ...
Artificial morality: Top-down, bottom
Artificial morality: Top-down, bottom

... incommensurable. While some economists may think that money provides a common measure (how much one is willing to spend to obtain some good or avoid some harm), this is controversial. But even if the problem of measurement could be solved, any topdown implementation of utilitarianism would have a lo ...
A Supervised Learning Approach to Musical Style Recognition
A Supervised Learning Approach to Musical Style Recognition

... Abstract. Musical style recognition is somehow intrinsic to human nature: the average layperson can tell the difference between a motet by Josquin and a symphony by Beethoven. But things change when it comes to computers. Musical style and its transformations take place in ways musicology is still u ...
Ventromedial frontal cortex mediates affective shifting in
Ventromedial frontal cortex mediates affective shifting in

... reversal phase of the experiment. Error bars show the 95% con®dence intervals. ...
A Developmental Approach to Intelligence
A Developmental Approach to Intelligence

... world and how to behave in it. In this way, simple reactive behavior can develop into time-dependent planned behavior. Innate knowledge is provided at Level 0, but in order to eliminate any preconceived notion of representation we assume that the relevant set of features at every subsequent level is ...
Transfer Learning through Indirect Encoding - Eplex
Transfer Learning through Indirect Encoding - Eplex

... to higher complexity states without altering the representation. The BEV representation is explained first, followed by its implementation, which is an ANN whose connectivity is trained by HyperNEAT. ...
IDA: A Cognitive Agent Architecture
IDA: A Cognitive Agent Architecture

... demon codelets. Their variables are bound in order that they can perform a particular task. When the task is ...
Dia 0 - TU/e
Dia 0 - TU/e

... meanings separately from data and content files, and separately from application code • In computer science and information science, an ontology formally represents knowledge as a set of concepts within a domain, and the relationships among those concepts. It can be used to reason about the entities ...
[pdf]
[pdf]

... to handle failures and recover from them. RPL is implemented as an extension to LISP and therefore provides all its functionality beside the planning constructs. RPL is not only a sophisticated representation for plans. Since it was designed for plan transformations, it provides explicit access to i ...
< 1 ... 15 16 17 18 19 20 21 22 23 ... 62 >

Concept learning

Concept learning, also known as category learning, concept attainment, and concept formation, is largely based on the works of the cognitive psychologist Jerome Bruner. Bruner, Goodnow, & Austin (1967) defined concept attainment (or concept learning) as ""the search for and listing of attributes that can be used to distinguish exemplars from non exemplars of various categories."" More simply put, concepts are the mental categories that help us classify objects, events, or ideas, building on the understanding that each object, event, or idea has a set of common relevant features. Thus, concept learning is a strategy which requires a learner to compare and contrast groups or categories that contain concept-relevant features with groups or categories that do not contain concept-relevant features.Concept learning also refers to a learning task in which a human or machine learner is trained to classify objects by being shown a set of example objects along with their class labels. The learner simplifies what has been observed by condensing it in the form of an example. This simplified version of what has been learned is then applied to future examples. Concept learning may be simple or complex because learning takes place over many areas. When a concept is difficult, it is less likely that the learner will be able to simplify, and therefore will be less likely to learn. Colloquially, the task is known as learning from examples. Most theories of concept learning are based on the storage of exemplars and avoid summarization or overt abstraction of any kind.
  • studyres.com © 2025
  • DMCA
  • Privacy
  • Terms
  • Report