A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Filters
Classification Transfer for Qualitative Reasoning Problems
2018
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
We study formalisms for temporal and spatial reasoning in the modern context of Constraint Satisfaction Problems (CSPs). ...
We then generalise our results for the Rectangle Algebra to the r-dimensional Block Algebra. ...
The central computational problem, designated the fundamental task of Qualitative Spatial and Temporal Reasoning in [Renz and Nebel, 2007] , has to do with the consistency of some partial information ...
doi:10.24963/ijcai.2018/175
dblp:conf/ijcai/BodirskyJMM18
fatcat:ixkuskf4vnbmbae3hupw5uad6u
Classification transfer for qualitative reasoning problems
[article]
2018
arXiv
pre-print
We study formalisms for temporal and spatial reasoning in the modern context of Constraint Satisfaction Problems (CSPs). ...
We then generalise our results for the Rectangle Algebra to the r-dimensional Block Algebra. ...
Acknowledgements We are grateful to our IJCAI reviewers for corrections to the first draft of the paper. ...
arXiv:1805.02038v1
fatcat:2kgfgwnuwzgb7pj7dlanmh6amu
The Case for Case-Based Transfer Learning
2011
The AI Magazine
We illustrate how CBR and transfer learning interact and characterize three approaches for using CBR in transfer learning: (1) as a transfer learning method, (2) for problem learning, and (3) to transfer ...
Case-based reasoning (CBR) is a problem-solving process in which a new problem is solved by retrieving a similar situation and reusing its solution. ...
Acknowledgements The authors would like to thank the reviewers for their helpful comments. Matthew Klenk is supported by an NRC Postdoctoral Fellowship.
Notes ...
doi:10.1609/aimag.v32i1.2331
fatcat:hcxcepesrzdtdgmejriazlprt4
Automatic Classification of Rhetorical Roles for Sentences: Comparing Rule-Based Scripts with Machine Learning
2019
International Conference on Artificial Intelligence and Law
(including semantic viewers, semantic search, decision summarizers, argument recommenders, and reasoning monitors). ...
use cases, and whether semantic attribution theory provides a general methodology for developing such classifiers. ...
Deane School of Law for its support for the Research Laboratory for Law, Logic and Technology. ...
dblp:conf/icail/WalkerPDLP19
fatcat:jkbkoj4zf5hddcaibqvc7obhdi
Event Tree as a Classification Model
2015
Science Research
In this paper event tree model as qualitative support method was used. This is applied to fault tree analysis. Transfer and transformation facts and rules for problem solving were described. ...
Method for knowledge extraction was presented. Mechanism of decision making and conclusions was implemented. Faults detection and classification were examined. ...
Acknowledgment The authors wish to express their gratitude to the Fund of Serbia for financial support. ...
doi:10.11648/j.sr.20150303.12
fatcat:ro6bczge65bwfkpo7wsdinmhnq
Explainable AI: The New 42?
[chapter]
2018
Lecture Notes in Computer Science
Acknowledgements The authors thanks their colleagues from local and international institutions for their valuable feedback, remarks and critics on this introduction to the MAKE-Explainable-AI workshop. ...
Right: VQA-X qualitative results: For each image the PJ-X model provides an answer and a justification, and points to the evidence for that justification. ...
Fig. 4 . 4 Left: ACT-X qualitative results: For each image the PJ-X model provides an answer and a justification, and points to the evidence for that justification. ...
doi:10.1007/978-3-319-99740-7_21
fatcat:v45udryxvngcfjpvj6s67ekdcq
Wine Quality Assessment Under The Eindhoven Classification Method
2019
ECMS 2019 Proceedings edited by Mauro Iacono, Francesco Palmieri, Marco Gribaudo, Massimo Ficco
The identification, classification and recording of events leading to deterioration of wine quality is essential for developing appropriate strategies to avoid them. ...
Logic Programming (LP) was used for Knowledge Representation and Reasoning (KRR) in order to model the universe of discourse, even in the presence of incomplete data, information or knowledge. ...
., it is given in the form of energy transfer operations as it will be shown below), therefore allowing for the handling of qualitative and quantitative data or knowledge, being it either incomplete, selfcontradictory ...
doi:10.7148/2019-0158
dblp:conf/ecms/PereiraCFAFRC0V19
fatcat:bogen23wmjchnewz3oedsksgxa
Encapsulating the Impact of Transfer Learning, Domain Knowledge and Training Strategies in Deep-Learning Based Architecture: A Biometric Based Case Study
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
In this paper, efforts have been made to analyze the impact of training strategies, transfer learning and domain knowledge on two biometric-based problems namely: three class oculus classification and ...
For analyzing these problems we have considered deep-learning based architecture and evaluated our results on benchmark contact-lens datasets like IIIT-D, ND, IIT-K (our model is publicly available) and ...
in real-world scenarios for large datasets and that too at a reasonable cost. ...
doi:10.1109/cvprw.2018.00242
dblp:conf/cvpr/SinghN18
fatcat:qb4272snanfkbewfp4cwdcknq4
CCS-GAN: COVID-19 CT-scan classification with very few positive training images
[article]
2021
arXiv
pre-print
CCS-GAN combines style transfer with pulmonary segmentation and relevant transfer learning from negative images in order to create a larger volume of synthetic positive images for the purposes of improving ...
diagnostic classification performance. ...
By comparison, the CCS-GAN is able to produce qualitatively reasonable results showing pulmonary features. ...
arXiv:2110.01605v1
fatcat:254jjytfzjb4jd5p7oydvp6ivi
Scrutiny of Critical Thinking Concept
2015
International Education Studies
It is used to describe the sample that includes information based on the qualitative research goals. ...
While philosophers emphasis on the nature and quality of critical thinking, psychologists focus on cognitive process and components used to investigate the practical problems. ...
Limitations and Recommendations for Future Research Low speed of internet, lack of adequate access to scientific cites and lack of a suitable and powerful software for analyzing the qualitative data were ...
doi:10.5539/ies.v8n3p93
fatcat:w7ooudxqcff5ddebvvuhm4l3yi
Towards a Semi-automatic Semantic Approach for Satellite Image Analysis
2013
Procedia Computer Science
Nevertheless, the reason why they are highly appropriate for knowledge-based systems is their ability to learn, i.e. to incorporate new statements derived from experience. ...
We highlight here the propositions that seem pertinent to tackle the semantic gap problem. Puissant et al. [4] made use of data mining processes for multi-level interpretation of multi-source images. ...
There exist three types of rules: • rules for addressing the symbol anchoring problem, explained in section 3.2.1, • rules for qualitative spatial reasoning, detailed in section 3.2.2, • rules to express ...
doi:10.1016/j.procs.2013.11.057
fatcat:qdsru5dhlvem3dktyiwgr4bgau
Page 425 of Contemporary Psychology Vol. 13, Issue 8
[page]
1968
Contemporary Psychology
Each of the four contribu- tors came to the campus for a three-day period during which he delivered his lecture on problems of classification. ...
He holds that “diagnoses cur- rently in use are more a nomenclature than a system of classification” and doubts that “we will ever be able to develop a natural system of classifica- tion based upon a qualitatively ...
Analogy and Relational Representations in the Companion Cognitive Architecture
2017
The AI Magazine
We also discuss three lessons learned and highlight three important open problems for cognitive systems research more broadly. ...
Our two central hypotheses about how to achieve this are (1) analogical reasoning and learning are central to cognition, and (2) qualitative representations provide a level of description that facilitates ...
Acknowledgments We thank the Office of Naval Research, the Air Force Office of Scientific Research, the National Science Foundation, and the Defense Advanced Research Projects Agency for their support ...
doi:10.1609/aimag.v38i4.2743
fatcat:ex3vwybbjvg6xcg4ktdjkg646i
CPMetric: Deep Siamese Networks for Learning Distances Between Structured Preferences
[article]
2019
arXiv
pre-print
Representing, learning, and reasoning with preferences is an important area of study both within computer science and across the sciences. ...
We present CPDist, a novel neural network to address the problem of learning to measure the distance between structured preference representations. ...
problem. ...
arXiv:1809.08350v2
fatcat:x56zamb2yrhdfhuqeik3uz2e7y
A Qualitative Analysis of Shell Nouns Used by University Students from China and Sweden
2017
International Journal of Languages, Literature and Linguistics
Based on language transfer theory, this study tries to explain the differences in shell nouns used by Chinese and Swedish university students from the perspective of linguistics and culture. ...
We hope that the results of this study could provide useful insights for the teaching and learning of shell nouns. ...
This work was supported by the Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University (No. Z2017062). ...
doi:10.18178/ijlll.2017.3.3.126
fatcat:uzxleqefmze6rnhw67ntqljv4m
« Previous
Showing results 1 — 15 out of 175,647 results