检索结果-内蒙古大学图书馆

LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Oeldorf, Cedric Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

—Domains such as logo synthesis, in which the data has a high degree of multi-modality, still pose a challenge for generative adversarial networks (GANs). Recent research shows that progressive training (ProGAN) and mapping network extensions (StyleGAN) enable both increased training stability for higher dimensional problems and better feature separation within the embedded latent space. However, these architectures leave limited control over shaping the output of the network, which is an undesirable trait in the case of logo synthesis. This paper explores a conditional extension to the StyleGAN architecture with the aim of firstly, improving on the low resolution results of previous research and, secondly, increasing the controllability of the output through the use of synthetic class-conditions. Furthermore, methods of extracting such class conditions are explored with a focus on the human interpretability, where the challenge lies in the fact that, by nature, visual logo characteristics are hard to define. The introduced conditional style-based generator architecture is trained on the extracted class-conditions in two experiments and studied relative to the performance of an unconditional model. Results show that, whilst the unconditional model more closely matches the training distribution, high quality conditions enabled the embedding of finer details onto the latent space, leading to more diverse output. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

An empirical evaluation of two general game systems: Ludii and RBG

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Piette, Éric Stephenson, Matthew Soemers, Dennis J.N.J. Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Although General Game Playing (GGP) systems can facilitate useful research in Artificial Intelligence (AI) for game-playing, they are often computationally inefficient and somewhat specialised to a specific class of games. However, since the start of this year, two General Game Systems have emerged that provide efficient alternatives to the academic state of the art - the Game Description Language (GDL). In order of publication, these are the Regular Boardgames language (RBG), and the Ludii system. This paper offers an experimental evaluation of Ludii. Here, we focus mainly on a comparison between the two new systems in terms of two key properties for any GGP system: simplicity/clarity (e.g. human-readability), and efficiency. Copyright © 2019, The Authors. All rights reserved.

关键词： knowledge representation

Learning policies from self-play with policy gradients and MCTS value estimates

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Soemers, Dennis J.N.J. Piette, Éric Stephenson, Matthew Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

In recent years, state-of-the-art game-playing agents often involve policies that are trained in self-playing processes where Monte Carlo tree search (MCTS) algorithms and trained policies iteratively improve each other. The strongest results have been obtained when policies are trained to mimic the search behaviour of MCTS by minimising a cross-entropy loss. Because MCTS, by design, includes an element of exploration, policies trained in this manner are also likely to exhibit a similar extent of exploration. In this paper, we are interested in learning policies for a project with future goals including the extraction of interpretable strategies, rather than state-of-the-art game-playing performance. For these goals, we argue that such an extent of exploration is undesirable, and we propose a novel objective function for training policies that are not exploratory. We derive a policy gradient expression for maximising this objective function, which can be estimated using MCTS value estimates, rather than MCTS visit counts. We empirically evaluate various properties of resulting policies, in a variety of board games. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

Learning from partially labeled data 28

学校读者我要写书评

暂无评论

Learning from partially labeled data

28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2020

作者： Mehrkanoon, Siamak Huang, Xiaolin Suykens, Johan A.K. Department of Data Science and Knowledge Engineering Maastricht University Netherlands Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Department of Electrical Engineering ESAT-STADIUS KU Leuven LeuvenB-3001 Belgium

ISBN: (纸本)9782875870742

Providing sufficient labeled training data in many application domains is a laborious and costly task. Designing models that can learn from partially labeled data, or leveraging labeled data in one domain and unlabeled data in a different but related domain is of great interest in many applications. In particular, in this context one can refer to semi-supervised modelling, transfer learning, domain adaptation and multi-view learning among oth- ers. There are several possibilities for designing such models ranging from shallow to deep models. These type of models have received increasing in- terest due to their successful applications in real-life problems. This paper provides a brief overview of recent techniques in learning from partially labeled data. © ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.

关键词： Neural networks

Partitioning vectors into quadruples: Worst-case analysis of a matching-based algorithm 29

学校读者我要写书评

暂无评论

Partitioning vectors into quadruples: Worst-case analysis of...

29th International Symposium on Algorithms and Computation, ISAAC 2018

作者： Ficker, Annette M.C. Erlebach, Thomas Mihalák, Matúš Spieksma, Frits C.R. Faculty of Economics and Business KU Leuven Leuven Belgium Department of Informatics University of Leicester Leicester United Kingdom Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands

ISBN: (纸本)9783959770941

Consider a problem where 4k given vectors need to be partitioned into k clusters of four vectors each. A cluster of four vectors is called a quad, and the cost of a quad is the sum of the component-wise maxima of the four vectors in the quad. The problem is to partition the given 4k vectors into k quads with minimum total cost. We analyze a straightforward matching-based algorithm and prove that this algorithm is a23 -approximation algorithm for this problem. We further analyze the performance of this algorithm on a hierarchy of special cases of the problem and prove that, in one particular case, the algorithm is a54 -approximation algorithm. Our analysis is tight in all cases except one. © Annette M. C. Ficker, Thomas Erlebach, Matúš Mihalák, and Frits C. R. Spieksma;licensed under Creative Commons License CC-BY

关键词： Approximation algorithms

Exploring the Role of Generative AI in Constructing knowledge Graphs for Drug Indications with Medical Context 15

学校读者我要写书评

暂无评论

Exploring the Role of Generative AI in Constructing Knowledg...

15th International Conference on Semantic Web Applications and Tools for Health Care and Life sciences, SWAT4HCLS 2024

作者： Alharbi, Reham Ahmed, Umair Dobriy, Daniil Lajewska, Weronika Menotti, Laura Saeedizade, Mohammad Javad Dumontier, Michel Department of Computer Science University of Liverpool Liverpool United Kingdom School of Science and Technology University of Camerino Camerino Italy Institute for Data Process and Knowledge Management Vienna University of Economics and Business Vienna Austria Department of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway Department of Information Engineering University of Padua Padova Italy Department of Computer Science Linköping University Linköping Sweden Institute of Data Science Maastricht University Maastricht Netherlands

The medical context for a drug indication provides crucial information on how the drug can be used in practice. However, the extraction of medical context from drug indications remains poorly explored, as most research concentrates on the recognition of medications and associated diseases. Indeed, most databases cataloging drug indications do not contain their medical context in a machine-readable format. This paper proposes the use of a large language model for constructing DIAMOND-KG, a knowledge graph of drug indications and their medical context. The study 1) examines the change in accuracy and precision in providing additional instruction to the language model, 2) estimates the prevalence of medical context in drug indications, and 3) assesses the quality of DIAMOND-KG against NeuroDKG, a small manually curated knowledge graph. The results reveal that more elaborated prompts improve the quality of extraction of medical context;71% of indications had at least one medical context;63.52% of extracted medical contexts correspond to those identified in NeuroDKG. This paper demonstrates the utility of using large language models for specialized knowledge extraction, with a particular focus on extracting drug indications and their medical context. We provide DIAMOND-KG as a FAIR RDF graph supported with an ontology. Openly accessible, DIAMOND-KG may be useful for downstream tasks such as semantic query answering, recommendation engines, and drug repositioning research. © 2024 Copyright for this paper by its authors.

关键词： knowledge graph

A retrieval-based dialogue system utilizing utterance and context embeddings

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Bartl, Alexander Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University MD6200 Netherlands

Finding semantically rich and computerunderstandable representations for textual dialogues, utterances and words is crucial for dialogue systems (or conversational agents), as their performance mostly depends on understanding the context of conversations. Recent research aims at finding distributed vector representations (embeddings) for words, such that semantically similar words are relatively close within the vector-space. Encoding the "meaning" of text into vectors is a current trend, and text can range from words, phrases and documents to actual human-to-human conversations. In recent research approaches, responses have been generated utilizing a decoder architecture, given the vector representation of the current conversation. In this paper, the utilization of embeddings for answer retrieval is explored by using Locality-Sensitive Hashing Forest (LSH Forest), an Approximate Nearest Neighbor (ANN) model, to find similar conversations in a corpus and rank possible candidates. Experimental results on the well-known Ubuntu Corpus (in English) and a customer service chat dataset (in Dutch) show that, in combination with a candidate selection method, retrieval-based approaches outperform generative ones and reveal promising future research directions towards the usability of such a system. Copyright © 2017, The Authors. All rights reserved.

关键词： Nearest neighbor search

Machine Memory Intelligence: Inspired by Human Memory Mechanisms

学校读者我要写书评

暂无评论

engineering 2025年

作者： Qinghua Zheng Huan Liu Xiaoqing Zhang Caixia Yan Xiangyong Cao Tieliang Gong Yong-Jin Liu Bin Shi Zhen Peng Xiaocen Fan Ying Cai Jun Liu School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Translational Research Institute of Brain and Brain-Like Intelligence Shanghai Fourth People’s Hospital Shanghai 200434 China School of Medicine Tongji University Shanghai 200092 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Department of Computer Science Iowa State University Ames IA 50011 USA

Large models, exemplified by ChatGPT, have reached the pinnacle of contemporary artificial intelligence (AI). However, they are plagued by three inherent drawbacks: excessive training data and computing power consumption, susceptibility to catastrophic forgetting, and a deficiency in logical reasoning capabilities within black-box models. To address these challenges, we draw insights from human memory mechanisms to introduce “machine memory,” which we define as a storage structure formed by encoding external information into a machine-representable and computable format. Centered on machine memory, we propose the brand-new machine memory intelligence (M 2 I) framework, which encompasses representation, learning, and reasoning modules and loops. We explore the key issues and recent advances in the four core aspects of M 2 I, including neural mechanisms, associative representation, continual learning, and collaborative reasoning within machine memory. M 2 I aims to liberate machine intelligence from the confines of data-centric neural networks and fundamentally break through the limitations of existing large models, driving a qualitative leap from weak to strong AI.

关键词： Machine memory intelligence Neural mechanism Associative representation Continual learning Collaborative reasoning

Spatial Relationship between Atrial Fibrillation Drivers and the Presence of Repetitive Conduction Patterns Using Recurrence Analysis on In-Silico Models

学校读者我要写书评

暂无评论

Spatial Relationship between Atrial Fibrillation Drivers and...

2021 Computing in Cardiology, CinC 2021

作者： Marques, Victor G Gharaviri, Ali Pezzuto, Simone Bonizzi, Pietro Zeemering, Stef Schotten, Ulrich Maastricht University Physiology Department Maastricht Netherlands Università della Svizzera Italiana Center for Computational Medicine in Cardiology Euler Institute Lugano Switzerland Maastricht University Department of Data Science and Knowledge Engineering Maastricht Netherlands

ISBN: (纸本)9781665479165

Catheter ablation treatment for atrial fibrillation (AF) is still suboptimal, possibly due to the difficulty to identify AF drivers. Recurrence analysis can be used to detect and eventually locate repetitive patterns that tend to be generated by AF drivers. In this study, we aimed to understand the spatial relationship between repetitiveness in recurrence analysis and rotor positions in an in-silico AF model. AF was simulated in a detailed three-dimensional model of the atria considering different degrees of endomysial fibrosis (0% and 70%). Rotors driving AF were tracked based on phase singularities obtained from transmembrane potentials. Activation-phase signals calculated from electrograms (4×4 electrode grid, 3 mm spacing) were used for recurrence analysis. Intervals with and without long-lasting sources inside the electrode coverage area were determined;the recurrence in both groups of intervals was quantified and compared with each other by calculating the recurrence rate (RR) per AF cycle length. RRs were lower during intervals with sources for both 0% and 70% fibrosis groups (0.56 [0.36;0.85] vs. 0.90 [0.80;0.97], p © 2021 Creative Commons.

关键词： Diseases