8,012 Hits in 5.9 sec

Decoding Digits and Dice with Magnetoencephalography: Evidence for a Shared Representation of Magnitude

Lina Teichmann, Tijl Grootswagers, Thomas Carlson, Anina N. Rich
2018 Journal of Cognitive Neuroscience  
The results show that we can cross-10 decode magnitude when training the classifier on magnitude presented in one symbolic 11 format and testing the classifier on the other symbolic format.  ...  Additionally, results from a time-generalisation 13 analysis show that digits were accessed slightly earlier than dice, demonstrating temporal 14 asynchronies in their shared representation of magnitude  ...  and (2) can a classifier trained on one numerical 55 symbol successfully generalise to another symbol?  ... 
doi:10.1162/jocn_a_01257 pmid:29561240 fatcat:knd5dwwh7vg6fdxv7ngevss4oi

Decoding digits and dice with Magnetoencephalography: Evidence for a shared representation of magnitude [article]

Lina Teichmann, Tijl Grootswagers, Thomas Carlson, Anina Rich
2018 bioRxiv   pre-print
The results show that we can cross-decode magnitude when training the classifier on magnitude presented in one symbolic format and testing the classifier on the other symbolic format.  ...  Additionally, results from a time-generalisation analysis show that digits were accessed slightly earlier than dice, demonstrating temporal asynchronies in their shared representation of magnitude.  ...  and (2) can a classifier trained on one numerical 55 symbol successfully generalise to another symbol?  ... 
doi:10.1101/249342 fatcat:v2kwg5brz5cuxpctks6q45mjy4

Predicting Affordances from Gist [chapter]

Pedro Santana, Cristina Santos, David Chaínho, Luís Correia, José Barata
2010 Lecture Notes in Computer Science  
The focus on affordances, rather than on objects, enables a self-supervised learning mechanism without assuming the existence of symbolic object representations, thus facilitating its integration on a  ...  The proposed model aims at helping the agent on the prioritisation of its perceptual resources, and consequently on visual attention.  ...  In Section 3, the results are shown and discussed, depicting the system's prediction and generalisation capabilities. The article ends by discussing the obtained results and future issues.  ... 
doi:10.1007/978-3-642-15193-4_31 fatcat:3zgwlqnb2fa6xoqdbvbulkhfhi

Prior familiarity with components enhances unconscious learning of relations

Ryan B. Scott, Zoltan Dienes
2010 Consciousness and Cognition  
Familiarity with the symbols increased the learning of relations between them (bigrams and trigrams) thus resulting in greater familiarity for grammatical versus ungrammatical strings.  ...  Familiarity with elemental components did not increase conscious awareness of the basis for discriminations (structural knowledge) but increased accuracy even in its absence.  ...  There is taken to be unconscious structural knowledge where there is above-chance classification accuracy in responses attributed to random selection, intuition, or familiarity, and to be conscious structural  ... 
doi:10.1016/j.concog.2009.12.012 pmid:20096605 fatcat:kknyxoqmhbhp3nitjxzlx5mcq4

Why Generalisability is not Generalisable

2006 Journal of Philosophy of Education  
The kind and the knowledge grow together ...  ...  In discourse, these categories and causes about human kinds become part of knowledge, of which we humans are both subject and object.  ... 
doi:10.1111/j.1467-9752.2006.00520.x fatcat:uismfkpdsbawbeaw63tvy4efjy

Emotion and polarity prediction from Twitter

Rebeen Ali Hamad, Saeed M. Alqahtani, Mercedes Torres Torres
2017 2017 Computing Conference  
Such an approach was used to collect real time Twitter microblogging data tweets towards mentioning iPad and iPhone in different locations in order to analyse and classify data in terms of polarity: positive  ...  Classification of public information from microblogging and social networking services could yield interesting outcomes and insights into the social and public opinions towards different services, products  ...  In 2011, Zhai et al. proposed an unsupervised method for sentiment classification in order to identify the evaluative sentences in the online review, achieving an F-score of 76% [16] .  ... 
doi:10.1109/sai.2017.8252118 fatcat:7y2kz4njwvasvin3o4bzoludim

Neurofuzzy Modelling and Pattern Matching for Online Fault Detection and Isolation of Nonlinear DC Motors

H.T. Mok, C.W. Chan
2008 IFAC Proceedings Volumes  
An online fault detection and isolation scheme for nonlinear systems based on neurofuzzy modelling and pattern matching is developed in this paper.  ...  Faults are isolated online by comparing these fuzzy rules with those in the fault database using a nearest neighbour classifier.  ...  Fuzzy systems allow symbolic generalisation of numerical data by fuzzy IF-THEN linguistic rules, which can be more readily understood by operators (de Miguel and Blázquez, 2005) .  ... 
doi:10.3182/20080706-5-kr-1001.00778 fatcat:ntlgwvrehfaitipclbwgrwegii

Building Affordance Relations for Robotic Agents - A Review [article]

Paola Ardón, Èric Pairet, Katrin S. Lohan, Subramanian Ramamoorthy, Ronald P. A. Petrick
2021 arXiv   pre-print
transfer, in the sense of implementations, to artificial intelligence (AI)-based systems and robotics.  ...  In this survey, we review and find common ground amongst different strategies that use the concept of affordances within robotic tasks, and build on these methods to provide guidance for including affordances  ...  Moreover, variations in the processing and learning of the data (as detailed in Section 3) constitute different levels of prior affordance relation knowledge, which closely influences the generalisation  ... 
arXiv:2105.06706v1 fatcat:prnjudntybaftfoq4gi5cjlpkm

Automated Fact-Checking: A Survey [article]

Xia Zeng, Amani S. Abumansour, Arkaitz Zubiaga
2021 arXiv   pre-print
As online false information continues to grow, automated fact-checking has gained an increasing amount of attention in recent years.  ...  Researchers in the field of Natural Language Processing (NLP) have contributed to the task by building fact-checking datasets, devising automated fact-checking pipelines and proposing NLP methods to further  ...  Acknowledgments This work was supported by the Engineering and Physical Sciences Research Council (grant EP/V048597/1). Xia Zeng is funded by China Scholarship Council (CSC). Amani S.  ... 
arXiv:2109.11427v1 fatcat:6ezha6y5svf4zkq7brodmd3vke

EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case [article]

Natalia Díaz-Rodríguez, Alberto Lamas, Jules Sanchez, Gianni Franchi, Ivan Donadello, Siham Tabik, David Filliat, Policarpo Cruz, Rosana Montes, Francisco Herrera
2021 arXiv   pre-print
In contrast, symbolic AI systems that convert concepts into rules or symbols -- such as knowledge graphs -- are easier to explain. However, they present lower generalisation and scaling capabilities.  ...  We tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph.  ...  Symbolic knowledge representation for including human experts in the loop Symbolic AI methods are interpretable and intuitive (e.g. they use rules, language, ontologies, fuzzy logics, etc.).  ... 
arXiv:2104.11914v1 fatcat:zqlpatbm2fa43e6zmfstz2u67i

Investigating possibilities of mathematical models to identify at-risk students in the South African context

Vaughan van Appel
2019 Perspectives in Education  
Statistical knowledge is included in a variety of programmes offered by many faculties at tertiary level, and early prediction of at-risk students seems necessary to enhance academic success especially  ...  Grounded on Meyer's model evaluation criteria and striving for a balance between accuracy and simplicity, two out of five models are identified as viable predictive models in identifying at-risk students  ...  Among their promising covariates were the number of times a student logged into their online course portal, and their participation in an online forum for the course.  ... 
doi:10.18820/2519593x/pie.v37i2.1 fatcat:uwncuqn4d5hzne5lftpwhe627i

Protocols from perceptual observations

Chris J. Needham, Paulo E. Santos, Derek R. Magee, Vincent Devin, David C. Hogg, Anthony G. Cohn
2005 Artificial Intelligence  
The PROGOL Inductive Logic Programming system is subsequently used to learn symbolic models of the temporal protocols presented in the presence of noise and overrepresentation in the symbolic data input  ...  Clustering within continuous feature spaces is used to learn object property and utterance models from processed sensor data, forming a symbolic description.  ...  We would like to thank Brandon Bennett and Aphrodite Galata for many useful discussions throughout the course of this research and also the anonymous reviewers for the comments that helped improve this  ... 
doi:10.1016/j.artint.2005.04.006 fatcat:6vmsva7xz5bcdklozj4ckxvoia

Complex knowledge modelling with functional entity relationship diagrams

Diarmuid J. Pigott, Valerie J. Hobbs
2011 Vine: The Journal of Information and Knowledge Management Systems  
of heterogeneous knowledge systems.  ...  entailment: instance-dominant, valuedominant, and connection-dominant.  ...  , dwelling in the knowledge level while being epiphenomenal to but inherent in the symbol level 1 .  ... 
doi:10.1108/03055721111134817 fatcat:frsprvpq2jennln654df2qx7uu

Affordances in Robotic Tasks – A Survey [article]

Paola Ardón, Èric Pairet, Katrin S. Lohan, Subramanian Ramamoorthy, Ronald P. A. Petrick
2020 arXiv   pre-print
In this survey, we classify the literature and try to find common ground amongst different approaches with a view to application in robotics.  ...  Historically, the concept derives from the literature in psychology and cognitive science, where affordances are discussed in a way that makes it hard for the definition to be directly transferred to computational  ...  This classification is based on the use of prior knowledge that relates target object, action, and effects.  ... 
arXiv:2004.07400v1 fatcat:hiexg6suzvg6ld7cwjtzyz4qka

Prediction of Student's Performance based on Incremental Learning

Pallavi Kulkarni, Roshani Ade
2014 International Journal of Computer Applications  
It is necessary to use Student dataset in order to analyze student's performance for future improvements in study methods and overall curricular.  ...  Incremental learning technique is a way in which data is processed in chunks and the results are merged so as to possess less memory.  ...  Online learning is a way where one can capture knowledge from training instances which are already labelled and continuously updated.  ... 
doi:10.5120/17440-8211 fatcat:owqq7bshyjgexjywya3ybjlx5y
« Previous Showing results 1 — 15 out of 8,012 results