Filters








382 Hits in 5.7 sec

Knowledge Acquisition through Machine Learning: Minimising Expert's Effort

R. Blanco-Vega, J. Hernandez-Orallo, M.J. Ramirez-Quintana
Fourth International Conference on Machine Learning and Applications (ICMLA'05)  
With this data we train a machine learning model which mimics the expert's behaviour.  ...  Machine learning can be applied to solve the knowledge acquisition bottleneck in many areas where an expert makes predictions to single cases, such as diagnosis, estimation, etc.  ...  The results and the proposed methodology are then a step forward in making knowledge acquisition through machine learning much more practical and easy, which can help to solve the knowledge acquisition  ... 
doi:10.1109/icmla.2005.45 dblp:conf/icmla/Blanco-VegaHR05 fatcat:7bzcp3vqj5drth5malo2zq2yu4

Memory and attention in deep learning [article]

Hung Le
2021 arXiv   pre-print
As the ultimate goal of machine learning is to derive intelligent systems that learn and act automatically just like human, memory construction for machine is inevitable.  ...  Attention mechanisms are derived to support acquisition and retention operations on the external memory.  ...  (2019) confirmed the existence of semantic memory in neural network by theoretically describing the trajectory of knowledge acquisition and organisation of neural semantic representations.  ... 
arXiv:2107.01390v1 fatcat:nxxjns7qdfb2fhe53qwwylagui

Authentic Learning Environments [chapter]

Jan Herrington, Thomas C. Reeves, Ron Oliver
2013 Handbook of Research on Educational Communications and Technology  
and real-life learning.  ...  One theory of learning which has the capacity to promote authentic learning is that of situated learning. vi Table of contents Abstract ii Declaration iv  ...  by Jonassen (1991b) as 'advanced knowledge acquisition' (p. 32).  ... 
doi:10.1007/978-1-4614-3185-5_32 fatcat:vvm2car6r5aulduwofly2u7o3u

Developing inclusive e-learning systems

Anthony Savidis, Dimitris Grammenos, Constantine Stephanidis
2006 Universal Access in the Information Society  
Inclusive e-learning is the outcome from the application of e-inclusion design and implementation methods in the context of e-learning systems.  ...  In this context, the primary emphasis is placed on the reporting of the design and implementation aspects to accommodate the inclusive system characteristics, rather than on the typical e-learning software  ...  e-Learning and accessibility Currently, there are a number of relevant important standardization efforts for e-learning content.  ... 
doi:10.1007/s10209-006-0024-1 fatcat:ps5yko35ergezgbc3c5v5apdke

Learning Robust Real-Time Cultural Transmission without Human Data [article]

Cultural General Intelligence Team, Avishkar Bhoopchand, Bethanie Brownfield, Adrian Collister, Agustin Dal Lago, Ashley Edwards, Richard Everett, Alexandre Frechette, Yanko Gitahy Oliveira, Edward Hughes, Kory W. Mathewson, Piermaria Mendolicchio (+7 others)
2022 arXiv   pre-print
In humans, it is the inheritance process that powers cumulative cultural evolution, expanding our skills, tools and knowledge across generations.  ...  Further details of the hyperparameters used for learning are reported in Appendices C.2. Expert Dropout (ED) Cultural transmission requires the acquisition of new behaviours from others.  ...  The objective is to minimise the 1 distance between the ground truth and predicted relative positions.  ... 
arXiv:2203.00715v1 fatcat:vlf5er6b4nhytn7lubbe42vbaa

In-house development of scheduling decision support systems: case study for scheduling semiconductor device test operations

T. Freed, K. H. Doerr, T. Chang
2007 International Journal of Production Research  
We draw upon the literature and our field case to discuss some of the trade-offs between in-house development and off-the-shelf acquisition of software.  ...  Learning is the acquisition of knowledge; and knowledge, like wealth, may best accrue to those that already have an existing fund and facility to make use of it.  ...  In summary, the in-house development effort and the associated analysis, provided critical learning, knowledge and relationship-building for the re-engineering of the process.  ... 
doi:10.1080/00207540600818351 fatcat:ekyga4cm5fblzchvvmtehgpaim

Eliciting expertise [chapter]

Nigel Shadbolt
2005 Evaluation of Human Work, 3rd Edition  
Knowledge elicitation comprises a set of techniques and methods that attempt to elicit an expert's knowledge through some form of direct interaction with that expert.  ...  These systems range from classical knowledge-based systems through to structured intranets, from workflow support tools through to best practice guidelines.  ...  We would like to be able to use techniques that will minimise the effort spent in gathering, transcribing and analysing an expert's knowledge.  ... 
doi:10.1201/9781420055948.ch8 fatcat:54yjvsqjrbdivcamed23fuhbbe

About Faults, Errors, and Other Dangerous Things [chapter]

Matthias Rauterberg
1996 The Kluwer International Series in Engineering and Computer Science  
In this paper the traditional paradigm for learning and training of operators in complex systems is discussed and criticised.  ...  The most well known arguments against the AI-approach are presented and discussed in relation to expertise, intuition and implicit knowledge.  ...  To minimise the effort is the basic principle for each actual decision. The implicit knowledge about the anticipated effort comes from previous faults, errors and other dangerous behaviour.  ... 
doi:10.1007/978-1-4613-1447-9_20 fatcat:qvfwvfitkvgjpc3ljb5luoy5uy

Deep learning for time series classification [article]

Hassan Ismail Fawaz
2020 arXiv   pre-print
The sequential aspect of time series data requires the development of algorithms that are able to harness this temporal property, thus making the existing off-the-shelf machine learning models for traditional  ...  Subsequently, we made numerous contributions in this area, notably in the context of transfer learning, data augmentation, ensembling and adversarial attacks.  ...  by deep learning models trained through backpropagation.  ... 
arXiv:2010.00567v1 fatcat:6u4naewelzhdvmypxzdwxww5du

Explainable Artificial Intelligence for Developing Smart Cities Solutions

Dhavalkumar Thakker, Bhupesh Kumar Mishra, Amr Abdullatif, Suvodeep Mazumdar, Sydney Simpson
2020 Smart Cities  
Traditional Artificial Intelligence (AI) technologies used in developing smart cities solutions, Machine Learning (ML) and recently Deep Learning (DL), rely more on utilising best representative training  ...  It also has the distinct advantage of integrating experts' knowledge on defining the decision-making rules to represent the complex circumstances and using such knowledge to explain the results.  ...  Authors would like to thank the five experts from Bradford City Council who took part in the knowledge elicitation and evaluation process.  ... 
doi:10.3390/smartcities3040065 fatcat:up6gewcvzzhmfpcayynixpbao4

Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score

Alberto Diez-Olivan, Jose A. Pagan, Ricardo Sanz, Basilio Sierra
2017 Neurocomputing  
The learning framework is performed on the basis of a machine learning approach that combines constrained K-means clustering for outlier detection and fuzzy modeling of distances to normality.  ...  Experimental results show a fully comprehensive yet accurate prognostics approach, improving detection capabilities and knowledge management.  ...  This work is an effort to implement a novel machine learning based approach that aims to minimise the negative effects of unexpected breakdowns, providing a reliable fault detection and prediction strategy  ... 
doi:10.1016/j.neucom.2017.02.024 fatcat:hagis2qcrfbuhoeggdkiuyt3b4

Ahead by a Century: Tim Edgar, Machine-Learning and the Future of Anti-Avoidance

Benjamin Alarie
2020 Social Science Research Network  
the development and deployment of new technologies in our legal system. tim edgar, machine-learning, and the future of anti-avoidance ■ 625 The internal mechanisms for the improvement of tax law begin  ...  Innovations in machine-learning and artificial intelligence will yield powerful insights about tax law from the inside-providing new tools for taxpayers and their advisers to understand the current and  ...  On the evidence of Conway's historical research in this article, more work on the lessons learned for future tax policy design would be welcome.  ... 
doi:10.2139/ssrn.3607928 fatcat:bmuq2jyyc5er5m2gafupqlh2oq

Domain-specific Knowledge Graphs: A survey [article]

Bilal Abu-Salih
2021 arXiv   pre-print
This is leveraged by the underlying structure of the KG which underpins a better comprehension, reasoning and interpretation of knowledge for both human and machine.  ...  Knowledge Graphs (KGs) have made a qualitative leap and effected a real revolution in knowledge representation.  ...  Through semi-automatically extraction approach, the proposed model was capable to collect and import entities captured from a set of online resources using various NLP and machine learning algorithms.  ... 
arXiv:2011.00235v3 fatcat:oc2loewqdjfgvlapy4kmult5li

Knowledge Engineering [chapter]

2014 Encyclopedia of Social Network Analysis and Mining  
Knowledge Engineering is the aspect of systems engineering which addresses uncertain process requirements by emphasising the acquisition of knowledge about a process and representing this knowledge in  ...  a Knowledge Based System.  ...  automated knowledge acquisition & machine learning, and for natural language processing.  ... 
doi:10.1007/978-1-4614-6170-8_100788 fatcat:iiauuwgtdrhbpfgflleheaf6pu

Automatic denoising of functional MRI data: Combining independent component analysis and hierarchical fusion of classifiers

Gholamreza Salimi-Khorshidi, Gwenaëlle Douaud, Christian F. Beckmann, Matthew F. Glasser, Ludovica Griffanti, Stephen M. Smith
2014 NeuroImage  
Once trained through the hand-classification of a sufficient number of training datasets, the classifier can then automatically classify new datasets.  ...  Learning and Generalisation- The fundamental goal of machine learning is to generalise beyond the examples in the training set.  ...  A.5.1 Ensemble Learning in FIX In the early days of machine learning, many distinct approaches were proposed, each with its own strengths and weaknesses.  ... 
doi:10.1016/j.neuroimage.2013.11.046 pmid:24389422 pmcid:PMC4019210 fatcat:xciy54775fh7tg5hvekpyrypdu
« Previous Showing results 1 — 15 out of 382 results