28,564 Hits in 2.4 sec

On the Right Path: A Modal Logic for Supervised Learning [article]

Alexandru Baltag, Dazhu Li, Mina Young Pedersen
2019 arXiv   pre-print
To reason about strategies in this game, we develop a modal logic of supervised learning (SLL).  ...  Broadly, this work takes a small step towards studying the interaction between graph games, logics and formal learning theory.  ...  Velázquez-Quesada for their inspiring suggestions. We also wish to thank three anonymous LORI-VII referees for improvement comments.  ... 
arXiv:1909.08559v1 fatcat:la4du2u7n5frxkdhxvmgli2wyq

Towards Interval Temporal Logic Rule-Based Classification

Estrella Lucena-Sánchez, Emilio Muñoz-Velasco, Guido Sciavicco, Ionel Eduard Stan, Alessandro Vaccari
2019 International Conference of the Italian Association for Artificial Intelligence  
In this paper, we propose a temporal rulebased classifier based on interval temporal logic, that is able to learn a classification model for multivariate classified (abstracted) time series, and we discuss  ...  Supervised classification is one of the main computational tasks of modern Artificial Intelligence, and it is used to automatically extract an underlying theory from a set of already classified instances  ...  Temporal data sets have been first introduced in [15] , where a polynomial time finite model checking algorithm for formulas of HS has been proposed. Learning a rule-based supervised classifier.  ... 
dblp:conf/aiia/Lucena-SanchezM19 fatcat:p7alhetervfgjfjqxfmwh7uw3m

Page 6077 of Mathematical Reviews Vol. , Issue 2002H [page]

2002 Mathematical Reviews  
This work has a practical application in supervised learning pattern recog- nition.  ...  Production rules whose conclusions are accompanied by belief degrees are obtained by supervised learning from a train- ing set.  ... 

A Pragmatic Logic of Scientific Discovery [chapter]

Jean Sallantin, Christopher Dartnell, Mohammad Afshar
2006 Lecture Notes in Computer Science  
Using Institution Agents, we define a dialectic process to manage contradiction. This allows autoepistemic Institution Agents to learn from a supervised teaching process.  ...  To the best of our knowledge, this paper is the first attempt to formalise a pragmatic logic of scientific discovery in a manner such that it can be realised by scientists assisted by machines.  ...  Using Institution Agents, we define a dialectic process to manage contradiction. This allows autoepistemic Institution Agents to learn from a supervised teaching process.  ... 
doi:10.1007/11893318_24 fatcat:pplu6753wnc75brigsrfm2lnre

Aristotle's Square Revisited to Frame Discovery Science

Mohammad Afshar, Christopher Dartnell, Dominique Luzeaux, Jean Sallantin, Yannick Tognetti
2007 Journal of Computers  
Data mining can be seen as one step in this complex process of interactive learning of an empirical theory This paper uses the terminology from paraconsistent logic and paracomplete logic that extends  ...  learning processes to predict pharmaco-kinetic properties (ADME-T) and adverse side effects of therapeutic drug molecules.  ...  [23] gives a concrete usage of defeasible logic, that allows us to order rules and to supervise an IA, for example with another higher IA, as illustrated on Figure 13 . • Every Obligation of a lower  ... 
doi:10.4304/jcp.2.5.54-66 fatcat:d5tbqt2d7bdfblyzvbnxxrv2ni

Inferring Sentiments from Supervised Classification of Text and Speech cues using Fuzzy Rules

Srishti Vashishtha, Seba Susan
2020 Procedia Computer Science  
Our fuzzy approach has been compared with eight state-of-the-art techniques for supervised machine learning.  ...  Our fuzzy approach has been compared with eight state-of-the-art techniques for supervised machine learning.  ...  Zadeh et al. introduced a tensor fusion network learns intra-modality and inter-modality dynamics end-to-end in multimodal sentiment analysis [30] .  ... 
doi:10.1016/j.procs.2020.03.348 fatcat:ezdaaw6z4fhwrnedf35i7unxbi

Introduction to the special issue on learning semantics

Antoine Bordes, Léon Bottou, Ronan Collobert, Dan Roth, Jason Weston, Luke Zettlemoyer
2013 Machine Learning  
A growing number of efforts to develop machine learning approaches for semantic analysis now aim to find (in an automated way) these interpretations (Miller et al.  ...  A key ambition of AI is to render computers able to evolve and interact with the real world.  ...  We are also grateful to MLJ Editor-in-Chief, Peter Flach, for his encouraging support, and the editorial office for their consistent help.  ... 
doi:10.1007/s10994-013-5381-4 fatcat:7i5ubznmabewldc5asxj3xqfru

Data integration and machine learning

Xin Luna Dong, Theodoros Rekatsinas
2018 Proceedings of the VLDB Endowment  
For machine learning to be effective, one must utilize data from the greatest possible variety of sources; and this is why data integration plays a key role.  ...  data for their analytics exercises, and (3) we discuss open research challenges and opportunities that span across data integration and machine learning.  ...  Recent results in multi-modal information extraction [51] and multi-modal deep learning [34] provide positive evidence. Fast and Cheap Training Data for DI.  ... 
doi:10.14778/3229863.3229876 fatcat:atysarruwrdythlge46vwlkcxi

An Epistemic Approach to the Formal Specification of Statistical Machine Learning [article]

Yusuke Kawamoto
2020 arXiv   pre-print
Specifically, we introduce a formal model for supervised learning based on a Kripke model where each possible world corresponds to a possible dataset and modal operators are interpreted as transformation  ...  As far as we know, this is the first work that uses epistemic models and logical formulas to express statistical properties of machine learning, and would be a starting point to develop theories of formal  ...  Acknowledgements I would like to thank the reviewers for their helpful and insightful comments. I am also grateful to Gergei Bana for his useful comments on part of a preliminary manuscript.  ... 
arXiv:2004.12734v2 fatcat:eqsgfcdcjngntkingfrqy4ecxy

droidlet: modular, heterogenous, multi-modal agents [article]

Anurag Pratik, Soumith Chintala, Kavya Srinet, Dhiraj Gandhi, Rebecca Qian, Yuxuan Sun, Ryan Drew, Sara Elkafrawy, Anoushka Tiwari, Tucker Hart, Mary Williamson, Abhinav Gupta (+1 others)
2021 arXiv   pre-print
On the other hand, in the field of robotics, large-scale learning has always been difficult. Supervision is hard to gather and real world physical interactions are expensive.  ...  Furthermore, it brings together perception, language and action onto one platform, providing a path towards agents that learn from the richness of real world interactions.  ...  We hope the droidlet platform opens up new avenues of research in self-supervised learning, multi-modal learning, interactive learning, human-robot interaction and lifelong learning.  ... 
arXiv:2101.10384v1 fatcat:llxpj5s2vvdvzd5ecx54g7amza

Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition [article]

Razvan Brinzea, Bulat Khaertdinov, Stylianos Asteriadis
2022 arXiv   pre-print
Furthermore, we propose a flexible, general-purpose framework for performing multimodal self-supervised learning, named Contrastive Multiview Coding with Cross-Modal Knowledge Mining (CMC-CMKM).  ...  We extend a number of recent contrastive self-supervised approaches for the task of Human Activity Recognition, leveraging inertial and skeleton data.  ...  is defined according to the same logic.  ... 
arXiv:2205.10071v1 fatcat:gi55kd5fanh47poi3cvgv7dcrm

Ten-Year History of Social Network Logics in China

Fenrong Liu, Dazhu Li
2022 Asian Studies  
The paper presents a ten-year history of social network logics in China.  ...  It tells the story of how this new research area was started, how its research agenda was extended, and, in particular, how a focus on graph games developed.  ...  We thank Zhen Liang for providing a summary of his works, and Yi Wang for sharing his papers with us. We are grateful to Bo Chen for inviting us to this special issue.  ... 
doi:10.4312/as.2022.10.2.121-146 fatcat:qztxrkmpozgwxgvt4ihvut4wgm

Multi-Modal Curriculum Learning for Semi-Supervised Image Classification

Chen Gong, Dacheng Tao, Stephen J. Maybank, Wei Liu, Guoliang Kang, Jie Yang
2016 IEEE Transactions on Image Processing  
Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a "teacher", and design a Multi-Modal Curriculum Learning (MMCL) strategy  ...  Semi-supervised image classification aims to classify a large quantity of unlabeled images by harnessing typically scarce labeled images.  ...  Semi-supervised Image Classification Semi-supervised learning (SSL) [12] has been studied for a long history, which aims to classify a massive number of unlabeled examples given the existence of only  ... 
doi:10.1109/tip.2016.2563981 pmid:27168596 fatcat:fgothu5cpvgwfdx3ikzxfzjwje

Using Large Pre-Trained Models with Cross-Modal Attention for Multi-Modal Emotion Recognition [article]

Krishna D N
2021 arXiv   pre-print
We propose using large self-supervised pre-trained models for both audio and text modality with cross-modality attention for multimodal emotion recognition.  ...  We use the cross-modal attention [3] mechanism to learn alignment between audio and text representations from self-supervised models.  ...  The idea of self-supervised learning is to leverage unlabeled data to learn a good representation of data for downstream applications.  ... 
arXiv:2108.09669v1 fatcat:qyqkosuo4fbknitjotmqrxcuua

Review of Recent Deep Learning Based Methods for Image-Text Retrieval

Jianan Chen, Lu Zhang, Cong Bai, Kidiyo Kpalma
2020 2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)  
Extracting relevant information efficiently from large-scale multi-modal data is becoming a crucial problem of information retrieval.  ...  In this paper, we highlight key points of recent cross-modal retrieval approaches based on deep-learning, especially in the image-text retrieval context, and classify them into four categories according  ...  Pairwise learning proposes two-branch architecture; adversarial learning and interaction learning methods are based on it; attributes learning may become a popular trend for cross-modal retrieval tasks  ... 
doi:10.1109/mipr49039.2020.00042 dblp:conf/mipr/ChenZBK20 fatcat:fps5wiw4ezf7teko3vegaxq4tq
« Previous Showing results 1 — 15 out of 28,564 results