当前期刊: arXiv - CS - Artificial Intelligence Go to current issue    加入关注   
显示样式:        排序: IF: - GO 导出
我的关注
我的收藏
您暂时未登录!
登录
  • Exploring Bayesian Surprise to Prevent Overfitting and to Predict Model Performance in Non-Intrusive Load Monitoring
    arXiv.cs.AI Pub Date : 2020-09-16
    Richard Jones; Christoph Klemenjak; Stephen Makonin; Ivan V. Bajic

    Non-Intrusive Load Monitoring (NILM) is a field of research focused on segregating constituent electrical loads in a system based only on their aggregated signal. Significant computational resources and research time are spent training models, often using as much data as possible, perhaps driven by the preconception that more data equates to more accurate models and better performing algorithms. When

    更新日期:2020-09-17
  • Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News
    arXiv.cs.AI Pub Date : 2020-09-16
    Reuben Tan; Kate Saenko; Bryan A. Plummer

    Large-scale dissemination of disinformation online intended to mislead or deceive the general population is a major societal problem. Rapid progression in image, video, and natural language generative models has only exacerbated this situation and intensified our need for an effective defense mechanism. While existing approaches have been proposed to defend against neural fake news, they are generally

    更新日期:2020-09-17
  • RDF2Vec Light -- A Lightweight Approachfor Knowledge Graph Embeddings
    arXiv.cs.AI Pub Date : 2020-09-16
    Jan Portisch; Michael Hladik; Heiko Paulheim

    Knowledge graph embedding approaches represent nodes and edges of graphs as mathematical vectors. Current approaches focus on embedding complete knowledge graphs, i.e. all nodes and edges. This leads to very high computational requirements on large graphs such as DBpedia or Wikidata. However, for most downstream application scenarios, only a small subset of concepts is of actual interest. In this paper

    更新日期:2020-09-17
  • One head is better than two: a polynomial restriction for propositional definite Horn forgetting
    arXiv.cs.AI Pub Date : 2020-09-16
    Paolo Liberatore

    Logical forgetting is NP-complete even in the simple case of propositional Horn formulae. An algorithm previously introduced is improved by changing the input formula before running it. This enlarges the restriction that makes the algorithm polynomial and decreases its running time in other cases. The size of the resulting formula decreases consequently.

    更新日期:2020-09-17
  • Question Directed Graph Attention Network for Numerical Reasoning over Text
    arXiv.cs.AI Pub Date : 2020-09-16
    Kunlong Chen; Weidi Xu; Xingyi Cheng; Zou Xiaochuan; Yuyu Zhang; Le Song; Taifeng Wang; Yuan Qi; Wei Chu

    Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph

    更新日期:2020-09-17
  • Theory of Mind with Guilt Aversion Facilitates Cooperative Reinforcement Learning
    arXiv.cs.AI Pub Date : 2020-09-16
    Dung Nguyen; Svetha Venkatesh; Phuoc Nguyen; Truyen Tran

    Guilt aversion induces experience of a utility loss in people if they believe they have disappointed others, and this promotes cooperative behaviour in human. In psychological game theory, guilt aversion necessitates modelling of agents that have theory about what other agents think, also known as Theory of Mind (ToM). We aim to build a new kind of affective reinforcement learning agents, called Theory

    更新日期:2020-09-17
  • Job2Vec: Job Title Benchmarking with Collective Multi-View Representation Learning
    arXiv.cs.AI Pub Date : 2020-09-16
    Denghui Zhang; Junming Liu; Hengshu Zhu; Yanchi Liu; Lichen Wang; Pengyang Wang; Hui Xiong

    Job Title Benchmarking (JTB) aims at matching job titles with similar expertise levels across various companies. JTB could provide precise guidance and considerable convenience for both talent recruitment and job seekers for position and salary calibration/prediction. Traditional JTB approaches mainly rely on manual market surveys, which is expensive and labor-intensive. Recently, the rapid development

    更新日期:2020-09-17
  • An Imprecise Probability Approach for Abstract Argumentation based on Credal Sets
    arXiv.cs.AI Pub Date : 2020-09-16
    Mariela Morveli-Espinoza; Juan Carlos Nieves; Cesar Augusto Tacla

    Some abstract argumentation approaches consider that arguments have a degree of uncertainty, which impacts on the degree of uncertainty of the extensions obtained from a abstract argumentation framework (AAF) under a semantics. In these approaches, both the uncertainty of the arguments and of the extensions are modeled by means of precise probability values. However, in many real life situations the

    更新日期:2020-09-17
  • General DeepLCP model for disease prediction : Case of Lung Cancer
    arXiv.cs.AI Pub Date : 2020-09-15
    Mayssa Ben Kahla; Dalel Kanzari; Ahmed Maalel

    According to GHO (Global Health Observatory (GHO), the high prevalence of a large variety of diseases such as Ischaemic heart disease, stroke, lung cancer disease and lower respiratory infections have remained the top killers during the past decade. The growth in the number of mortalities caused by these disease is due to the very delayed symptoms'detection. Since in the early stages, the symptoms

    更新日期:2020-09-17
  • A Human-Computer Duet System for Music Performance
    arXiv.cs.AI Pub Date : 2020-09-16
    Yuen-Jen Lin; Hsuan-Kai Kao; Yih-Chih Tseng; Ming Tsai; Li Su

    Virtual musicians have become a remarkable phenomenon in the contemporary multimedia arts. However, most of the virtual musicians nowadays have not been endowed with abilities to create their own behaviors, or to perform music with human musicians. In this paper, we firstly create a virtual violinist, who can collaborate with a human pianist to perform chamber music automatically without any intervention

    更新日期:2020-09-17
  • CoDEx: A Comprehensive Knowledge Graph Completion Benchmark
    arXiv.cs.AI Pub Date : 2020-09-16
    Tara Safavi; Danai Koutra

    We present CoDEx, a set of knowledge graph Completion Datasets Extracted from Wikidata and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. In terms of scope, CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible

    更新日期:2020-09-17
  • GLUCOSE: GeneraLized and COntextualized Story Explanations
    arXiv.cs.AI Pub Date : 2020-09-16
    Nasrin Mostafazadeh; Aditya Kalyanpur; Lori Moon; David Buchanan; Lauren Berkowitz; Or Biran; Jennifer Chu-Carroll

    When humans read or listen, they make implicit commonsense inferences that frame their understanding of what happened and why. As a step toward AI systems that can build similar mental models, we introduce GLUCOSE, a large-scale dataset of implicit commonsense causal knowledge, encoded as causal mini-theories about the world, each grounded in a narrative context. To construct GLUCOSE, we drew on cognitive

    更新日期:2020-09-17
  • Scaffold-constrained molecular generation
    arXiv.cs.AI Pub Date : 2020-09-15
    Maxime Langevin; Herve Minoux; Maximilien Levesque; Marc Bianciotto

    One of the major applications of generative models for drug Discovery targets the lead-optimization phase. During the optimization of a lead series, it is common to have scaffold constraints imposed on the structure of the molecules designed. Without enforcing such constraints, the probability of generating molecules with the required scaffold is extremely low and hinders the practicality of generative

    更新日期:2020-09-17
  • TreeGAN: Incorporating Class Hierarchy into Image Generation
    arXiv.cs.AI Pub Date : 2020-09-16
    Ruisi Zhang; Luntian Mou; Pengtao Xie

    Conditional image generation (CIG) is a widely studied problem in computer vision and machine learning. Given a class, CIG takes the name of this class as input and generates a set of images that belong to this class. In existing CIG works, for different classes, their corresponding images are generated independently, without considering the relationship among classes. In real-world applications, the

    更新日期:2020-09-17
  • Leveraging Semantic Parsing for Relation Linking over Knowledge Bases
    arXiv.cs.AI Pub Date : 2020-09-16
    Nandana Mihindukulasooriya; Gaetano Rossiello; Pavan Kapanipathi; Ibrahim Abdelaziz; Srinivas Ravishankar; Mo Yu; Alfio Gliozzo; Salim Roukos; Alexander Gray

    Knowledgebase question answering systems are heavily dependent on relation extraction and linking modules. However, the task of extracting and linking relations from text to knowledgebases faces two primary challenges; the ambiguity of natural language and lack of training data. To overcome these challenges, we present SLING, a relation linking framework which leverages semantic parsing using Abstract

    更新日期:2020-09-17
  • AI-powered Covert Botnet Command and Control on OSNs
    arXiv.cs.AI Pub Date : 2020-09-16
    Zhi Wang; Chaoge Liu; Xiang Cui; Jialong Zhang; Di Wu; Jie Yin; Jiaxi Liu; Qixu Liu; Jinli Zhang

    Botnet is one of the major threats to computer security. In previous botnet command and control (C&C) scenarios using online social networks (OSNs), methods for finding botmasters (e.g. ids, links, DGAs, etc.) are hardcoded into bots. Once a bot is reverse engineered, botmaster is exposed. Meanwhile, abnormal contents from explicit commands may expose botmaster and raise anomalies on OSNs. To overcome

    更新日期:2020-09-17
  • Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude Coupling
    arXiv.cs.AI Pub Date : 2020-09-16
    Abdelhak Lemkhenter; Paolo Favaro

    Various hand-crafted features representations of bio-signals rely primarily on the amplitude or power of the signal in specific frequency bands. The phase component is often discarded as it is more sample specific, and thus more sensitive to noise, than the amplitude. However, in general, the phase component also carries information relevant to the underlying biological processes. In fact, in this

    更新日期:2020-09-17
  • Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition
    arXiv.cs.AI Pub Date : 2020-09-16
    Bianjiang Yang; Zi Hui; Haoji Hu; Xinyi Hu; Lu Yu

    Although the facial makeup transfer network has achieved high-quality performance in generating perceptually pleasing makeup images, its capability is still restricted by the massive computation and storage of the network architecture. We address this issue by compressing facial makeup transfer networks with collaborative distillation and kernel decomposition. The main idea of collaborative distillation

    更新日期:2020-09-17
  • Video Compression with CNN-based Post Processing
    arXiv.cs.AI Pub Date : 2020-09-16
    Fan Zhang; Di Ma; Chen Feng; David R. Bull

    In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content. Among various compression tools, post-processing can be applied on reconstructed video content to mitigate visible compression artefacts and to enhance overall perceptual quality. Inspired by advances in deep learning, we propose

    更新日期:2020-09-17
  • Brain tumour segmentation using cascaded 3D densely-connected U-net
    arXiv.cs.AI Pub Date : 2020-09-16
    Mina Ghaffari; Arcot Sowmya; Ruth Oliver

    Accurate brain tumour segmentation is a crucial step towards improving disease diagnosis and proper treatment planning. In this paper, we propose a deep-learning based method to segment a brain tumour into its subregions: whole tumour, tumour core and enhancing tumour. The proposed architecture is a 3D convolutional neural network based on a variant of the U-Net architecture of Ronneberger et al. [17]

    更新日期:2020-09-17
  • Group-wise Contrastive Learning for Neural Dialogue Generation
    arXiv.cs.AI Pub Date : 2020-09-16
    Hengyi Cai; Hongshen Chen; Yonghao Song; Zhuoye Ding; Yongjun Bao; Weipeng Yan; Xiaofang Zhao

    Neural dialogue response generation has gained much popularity in recent years. Maximum Likelihood Estimation (MLE) objective is widely adopted in existing dialogue model learning. However, models trained with MLE objective function are plagued by the low-diversity issue when it comes to the open-domain conversational setting. Inspired by the observation that humans not only learn from the positive

    更新日期:2020-09-17
  • Partial Bandit and Semi-Bandit: Making the Most Out of Scarce Users' Feedback
    arXiv.cs.AI Pub Date : 2020-09-16
    Alexandre Letard; Tassadit Amghar; Olivier Camp; Nicolas Gutowski

    Recent works on Multi-Armed Bandits (MAB) and Combinatorial Multi-Armed Bandits (COM-MAB) show good results on a global accuracy metric. This can be achieved, in the case of recommender systems, with personalization. However, with a combinatorial online learning approach, personalization implies a large amount of user feedbacks. Such feedbacks can be hard to acquire when users need to be directly and

    更新日期:2020-09-17
  • Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
    arXiv.cs.AI Pub Date : 2020-09-16
    Haoran Zhang; Qianying Liu; Aysa Xuemo Fan; Heng Ji; Daojian Zeng; Fei Cheng; Daisuke Kawahara; Sadao Kurohashi

    Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an unnecessary order on the unordered triplets and involves a large decoding length associated with error accumulation. These introduce exposure bias, which may cause the models overfit

    更新日期:2020-09-17
  • Path Planning using Neural A* Search
    arXiv.cs.AI Pub Date : 2020-09-16
    Ryo Yonetani; Tatsunori Taniai; Mohammadamin Barekatain; Mai Nishimura; Asako Kanezaki

    We present Neural A*, a novel data-driven search algorithm for path planning problems. Although data-driven planning has received much attention in recent years, little work has focused on how search-based methods can learn from demonstrations to plan better. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end

    更新日期:2020-09-17
  • Solomon at SemEval-2020 Task 11: Ensemble Architecture for Fine-Tuned Propaganda Detection in News Articles
    arXiv.cs.AI Pub Date : 2020-09-16
    Mayank Raj; Ajay Jaiswal; Rohit R. R; Ankita Gupta; Sudeep Kumar Sahoo; Vertika Srivastava; Yeon Hyang Kim

    This paper describes our system (Solomon) details and results of participation in the SemEval 2020 Task 11 "Detection of Propaganda Techniques in News Articles"\cite{DaSanMartinoSemeval20task11}. We participated in Task "Technique Classification" (TC) which is a multi-class classification task. To address the TC task, we used RoBERTa based transformer architecture for fine-tuning on the propaganda

    更新日期:2020-09-17
  • Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision
    arXiv.cs.AI Pub Date : 2020-09-16
    Sathyanarayanan N. Aakur; Sanjoy Kundu; Nikhil Gunti

    Advances in deep learning have enabled the development of models that have exhibited a remarkable tendency to recognize and even localize actions in videos. However, they tend to experience errors when faced with scenes or examples beyond their initial training environment. Hence, they fail to adapt to new domains without significant retraining with large amounts of annotated data. Current algorithms

    更新日期:2020-09-17
  • Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding
    arXiv.cs.AI Pub Date : 2020-09-16
    Martin Kuo; Yaobo Liang; Lei Ji; Nan Duan; Linjun Shou; Ming Gong; Peng Chen

    Question Aware Open Information Extraction (Question aware Open IE) takes question and passage as inputs, outputting an answer tuple which contains a subject, a predicate, and one or more arguments. Each field of answer is a natural language word sequence and is extracted from the passage. The semi-structured answer has two advantages which are more readable and falsifiable compared to span answer

    更新日期:2020-09-17
  • Grounded Adaptation for Zero-shot Executable Semantic Parsing
    arXiv.cs.AI Pub Date : 2020-09-16
    Victor Zhong; Mike Lewis; Sida I. Wang; Luke Zettlemoyer

    We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation

    更新日期:2020-09-17
  • Functional sets with typed symbols: Framework and mixed Polynotopes for hybrid nonlinear reachability and filtering
    arXiv.cs.AI Pub Date : 2020-09-15
    Christophe Combastel

    Verification and synthesis of Cyber-Physical Systems (CPS) are challenging and still raise numerous issues so far. In this paper, an original framework with mixed sets defined as function images of symbol type domains is first proposed. Syntax and semantics are explicitly distinguished. Then, both continuous (interval) and discrete (signed, boolean) symbol types are used to model dependencies through

    更新日期:2020-09-17
  • Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction
    arXiv.cs.AI Pub Date : 2020-09-15
    Rujun Han; Yichao Zhou; Nanyun Peng

    Extracting event temporal relations is a critical task for information extraction and plays an important role in natural language understanding. Prior systems leverage deep learning and pre-trained language models to improve the performance of the task. However, these systems often suffer from two short-comings: 1) when performing maximum a posteriori (MAP) inference based on neural models, previous

    更新日期:2020-09-17
  • Evaluating representations by the complexity of learning low-loss predictors
    arXiv.cs.AI Pub Date : 2020-09-15
    William F. Whitney; Min Jae Song; David Brandfonbrener; Jaan Altosaar; Kyunghyun Cho

    We consider the problem of evaluating representations of data for use in solving a downstream task. We propose to measure the quality of a representation by the complexity of learning a predictor on top of the representation that achieves low loss on a task of interest, and introduce two methods, surplus description length (SDL) and $\varepsilon$ sample complexity ($\varepsilon$SC). In contrast to

    更新日期:2020-09-17
  • Advancing the Scientific Frontier with Increasingly Autonomous Systems
    arXiv.cs.AI Pub Date : 2020-09-15
    Rashied Amini; Abigail Azari; Shyam Bhaskaran; Patricia Beauchamp; Julie Castillo-Rogez; Rebecca Castano; Seung Chung; John Day; Richard Doyle; Martin Feather; Lorraine Fesq; Jeremy Frank; P. Michael Furlong; Michel Ingham; Brian Kennedy; Ksenia Kolcio; Issa Nesnas; Robert Rasmussen; Glenn Reeves; Cristina Sorice; Bethany Theiling; Jay Wyatt

    A close partnership between people and partially autonomous machines has enabled decades of space exploration. But to further expand our horizons, our systems must become more capable. Increasing the nature and degree of autonomy - allowing our systems to make and act on their own decisions as directed by mission teams - enables new science capabilities and enhances science return. The 2011 Planetary

    更新日期:2020-09-17
  • Constrained Labeling for Weakly Supervised Learning
    arXiv.cs.AI Pub Date : 2020-09-15
    Chidubem Arachie; Bert Huang

    Curation of large fully supervised datasets has become one of the major roadblocks for machine learning. Weak supervision provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated labeling functions from varying sources. The key challenge in weakly supervised learning is combining the different weak supervision signals while navigating misleading correlations

    更新日期:2020-09-17
  • Autonomous Learning of Features for Control: Experiments with Embodied and Situated Agents
    arXiv.cs.AI Pub Date : 2020-09-15
    Nicola Milano; Stefano Nolfi

    As discussed in previous studies, the efficacy of evolutionary or reinforcement learning algorithms for continuous control optimization can be enhanced by including a neural module dedicated to feature extraction trained through self-supervised methods. In this paper we report additional experiments supporting this hypothesis and we demonstrate how the advantage provided by feature extraction is not

    更新日期:2020-09-16
  • Monotonicity in practice of adaptive testing
    arXiv.cs.AI Pub Date : 2020-09-15
    Martin Plajner; Jiří Vomlel

    In our previous work we have shown how Bayesian networks can be used for adaptive testing of student skills. Later, we have taken the advantage of monotonicity restrictions in order to learn models fitting data better. This article provides a synergy between these two phases as it evaluates Bayesian network models used for computerized adaptive testing and learned with a recently proposed monotonicity

    更新日期:2020-09-16
  • The Importance of Pessimism in Fixed-Dataset Policy Optimization
    arXiv.cs.AI Pub Date : 2020-09-15
    Jacob Buckman; Carles Gelada; Marc G. Bellemare

    We study worst-case guarantees on the expected return of fixed-dataset policy optimization algorithms. Our core contribution is a unified conceptual and mathematical framework for the study of algorithms in this regime. This analysis reveals that for naive approaches, the possibility of erroneous value overestimation leads to a difficult-to-satisfy requirement: in order to guarantee that we select

    更新日期:2020-09-16
  • Analysis of Models for Decentralized and Collaborative AI on Blockchain
    arXiv.cs.AI Pub Date : 2020-09-14
    Justin D. Harris

    Machine learning has recently enabled large advances in artificial intelligence, but these results can be highly centralized. The large datasets required are generally proprietary; predictions are often sold on a per-query basis; and published models can quickly become out of date without effort to acquire more data and maintain them. Published proposals to provide models and data for free for certain

    更新日期:2020-09-16
  • Report prepared by the Montreal AI Ethics Institute (MAIEI) for Publication Norms for Responsible AI by Partnership on AI
    arXiv.cs.AI Pub Date : 2020-09-15
    Abhishek GuptaMontreal AI Ethics InstituteMicrosoft; Camylle LanteigneMontreal AI Ethics InstituteAlgora Lab; Victoria HeathMontreal AI Ethics Institute

    The history of science and technology shows that seemingly innocuous developments in scientific theories and research have enabled real-world applications with significant negative consequences for humanity. In order to ensure that the science and technology of AI is developed in a humane manner, we must develop research publication norms that are informed by our growing understanding of AI's potential

    更新日期:2020-09-16
  • Food safety risk prediction with Deep Learning models using categorical embeddings on European Union data
    arXiv.cs.AI Pub Date : 2020-09-14
    Alberto Nogales; Rodrigo Díaz Morón; Álvaro J. García-Tejedor

    The world is becoming more globalized every day and people can buy products from almost every country in the world in their local stores. Given the different food and feed safety laws from country to country, the European Union began to register in 1977 all irregularities related to traded products to ensure cross-border monitoring of information and a quick reaction when risks to public health are

    更新日期:2020-09-16
  • BERT-QE: Contextualized Query Expansion for Document Re-ranking
    arXiv.cs.AI Pub Date : 2020-09-15
    Zhi Zheng; Kai Hui; Ben He; Xianpei Han; Le Sun; Andrew Yates

    Query expansion aims to mitigate the mismatch between the language used in a query and in a document. Query expansion methods can suffer from introducing non-relevant information when expanding the query, however. To bridge this gap, inspired by recent advances in applying contextualized models like BERT to the document retrieval task, this paper proposes a novel query expansion model that leverages

    更新日期:2020-09-16
  • PointIso: Point Cloud Based Deep Learning Model for Detecting Arbitrary-Precision Peptide Features in LC-MS Map through Attention Based Segmentation
    arXiv.cs.AI Pub Date : 2020-09-15
    Fatema Tuz Zohora; M Ziaur Rahman; Ngoc Hieu Tran; Lei Xin; Baozhen Shan; Ming Li

    A promising technique of discovering disease biomarkers is to measure the relative protein abundance in multiple biofluid samples through liquid chromatography with tandem mass spectrometry (LC-MS/MS) based quantitative proteomics. The key step involves peptide feature detection in LC-MS map, along with its charge and intensity. Existing heuristic algorithms suffer from inaccurate parameters since

    更新日期:2020-09-16
  • A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
    arXiv.cs.AI Pub Date : 2020-09-15
    Moin Nadeem; Tianxing He; Kyunghyun Cho; James Glass

    This work studies the widely adopted ancestral sampling algorithms for auto-regressive language models, which is not widely studied in the literature. We use the quality-diversity (Q-D) trade-off to investigate three popular sampling algorithms (top-k, nucleus and tempered sampling). We focus on the task of open-ended language generation. We first show that the existing sampling algorithms have similar

    更新日期:2020-09-16
  • Lessons Learned from Applying off-the-shelf BERT: There is no SilverBullet
    arXiv.cs.AI Pub Date : 2020-09-15
    Victor Makarenkov; Lior Rokach

    One of the challenges in the NLP field is training large classification models, a task that is both difficult and tedious. It is even harder when GPU hardware is unavailable. The increased availability of pre-trained and off-the-shelf word embeddings, models, and modules aim at easing the process of training large models and achieving a competitive performance. We explore the use of off-the-shelf BERT

    更新日期:2020-09-16
  • 3D_DEN: Open-ended 3D Object Recognition using Dynamically Expandable Networks
    arXiv.cs.AI Pub Date : 2020-09-15
    Sudhakaran Jain; Hamidreza Kasaei

    Service robots, in general, have to work independently and adapt to the dynamic changes in the environment. One important aspect in such scenarios is to continually learn to recognize new objects when they become available. This combines two main research problems namely continual learning and 3D object recognition. Most of the existing research approaches include the use of deep Convolutional Neural

    更新日期:2020-09-16
  • Critical Thinking for Language Models
    arXiv.cs.AI Pub Date : 2020-09-15
    Gregor Betz

    This paper takes a first step towards a critical thinking curriculum for neural auto-regressive language models. We introduce a synthetic text corpus of deductively valid arguments, and use this artificial argument corpus to train and evaluate GPT-2. Significant transfer learning effects can be observed: Training a model on a few simple core schemes allows it to accurately complete conclusions of different

    更新日期:2020-09-16
  • Graph Convolution Networks Using Message Passing and Multi-Source Similarity Features for Predicting circRNA-Disease Association
    arXiv.cs.AI Pub Date : 2020-09-15
    Thosini Bamunu Mudiyanselage; Xiujuan Lei; Nipuna Senanayake; Yanqing Zhang; Yi Pan

    Graphs can be used to effectively represent complex data structures. Learning these irregular data in graphs is challenging and still suffers from shallow learning. Applying deep learning on graphs has recently showed good performance in many applications in social analysis, bioinformatics etc. A message passing graph convolution network is such a powerful method which has expressive power to learn

    更新日期:2020-09-16
  • It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners
    arXiv.cs.AI Pub Date : 2020-09-15
    Timo Schick; Hinrich Schütze

    When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance on challenging natural language understanding benchmarks. In this work, we show that performance similar to GPT-3 can be obtained with language models whose parameter count is several orders of magnitude smaller. This is achieved by converting textual

    更新日期:2020-09-16
  • Polyp-artifact relationship analysis using graph inductive learned representations
    arXiv.cs.AI Pub Date : 2020-09-15
    Roger D. Soberanis-Mukul; Shadi Albarqouni; Nassir Navab

    The diagnosis process of colorectal cancer mainly focuses on the localization and characterization of abnormal growths in the colon tissue known as polyps. Despite recent advances in deep object localization, the localization of polyps remains challenging due to the similarities between tissues, and the high level of artifacts. Recent studies have shown the negative impact of the presence of artifacts

    更新日期:2020-09-16
  • Approximate spectral clustering using both reference vectors and topology of the network generated by growing neural gas
    arXiv.cs.AI Pub Date : 2020-09-15
    Kazuhisa Fujita

    Spectral clustering (SC) is one of the most popular clustering methods and often outperforms traditional clustering methods. SC uses the eigenvectors of a Laplacian matrix calculated from a similarity matrix of a dataset. SC has serious drawbacks that are the significant increase in the computational complexity derived from the eigendecomposition and the memory space complexities to store the similarity

    更新日期:2020-09-16
  • Machine learning predicts early onset of fever from continuous physiological data of critically ill patients
    arXiv.cs.AI Pub Date : 2020-09-14
    Aditya Singh; Akram Mohammed; Lokesh Chinthala; Rishikesan Kamaleswaran

    Fever can provide valuable information for diagnosis and prognosis of various diseases such as pneumonia, dengue, sepsis, etc., therefore, predicting fever early can help in the effectiveness of treatment options and expediting the treatment process. This study aims to develop novel algorithms that can accurately predict fever onset in critically ill patients by applying machine learning technique

    更新日期:2020-09-16
  • Second-order Neural Network Training Using Complex-step Directional Derivative
    arXiv.cs.AI Pub Date : 2020-09-15
    Siyuan Shen; Tianjia Shao; Kun Zhou; Chenfanfu Jiang; Feng Luo; Yin Yang

    While the superior performance of second-order optimization methods such as Newton's method is well known, they are hardly used in practice for deep learning because neither assembling the Hessian matrix nor calculating its inverse is feasible for large-scale problems. Existing second-order methods resort to various diagonal or low-rank approximations of the Hessian, which often fail to capture necessary

    更新日期:2020-09-16
  • MLMLM: Link Prediction with Mean Likelihood Masked Language Model
    arXiv.cs.AI Pub Date : 2020-09-15
    Louis Clouatre; Philippe Trempe; Amal Zouaq; Sarath Chandar

    Knowledge Bases (KBs) are easy to query, verifiable, and interpretable. They however scale with man-hours and high-quality data. Masked Language Models (MLMs), such as BERT, scale with computing power as well as unstructured raw text data. The knowledge contained within those models is however not directly interpretable. We propose to perform link prediction with MLMs to address both the KBs scalability

    更新日期:2020-09-16
  • Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks
    arXiv.cs.AI Pub Date : 2020-09-15
    Sagar Vaze; James Foley; Mohamed Seddiq; Alexey Unagaev; Natalia Efremova

    The analysis of satellite imagery will prove a crucial tool in the pursuit of sustainable development. While Convolutional Neural Networks (CNNs) have made large gains in natural image analysis, their application to multi-spectral satellite images (wherein input images have a large number of channels) remains relatively unexplored. In this paper, we compare different methods of leveraging multi-band

    更新日期:2020-09-16
  • Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems
    arXiv.cs.AI Pub Date : 2020-09-15
    Haoliang LiNanyang Technological University, Singapore; Yufei WangNanyang Technological University, Singapore; Xiaofei XieNanyang Technological University, Singapore; Yang LiuNanyang Technological University, Singapore; Shiqi WangCity University of Hong Kong; Renjie WanNanyang Technological University, Singapore; Lap-Pui ChauNanyang Technological University, Singapore; Alex C. KotNanyang Technological

    Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the targeted DNN is always available, and an attacker can always inject a specific pattern to the training data to further fine-tune the DNN model. However, in practice

    更新日期:2020-09-16
  • Gravitational Models Explain Shifts on Human Visual Attention
    arXiv.cs.AI Pub Date : 2020-09-15
    Dario Zanca; Marco Gori; Stefano Melacci; Alessandra Rufa

    Visual attention refers to the human brain's ability to select relevant sensory information for preferential processing, improving performance in visual and cognitive tasks. It proceeds in two phases. One in which visual feature maps are acquired and processed in parallel. Another where the information from these maps is merged in order to select a single location to be attended for further and more

    更新日期:2020-09-16
  • Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
    arXiv.cs.AI Pub Date : 2020-09-15
    Jang-Hyun Kim; Wonho Choo; Hyun Oh Song

    While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks. In this regard, a number of mixup based augmentation methods have been recently proposed. However, these approaches mainly focus on creating previously unseen virtual examples and can sometimes provide misleading supervisory

    更新日期:2020-09-16
  • Optimal Decision Trees for Nonlinear Metrics
    arXiv.cs.AI Pub Date : 2020-09-15
    Emir Demirović; Peter J. Stuckey

    Nonlinear metrics, such as the F1-score, Matthews correlation coefficient, and Fowlkes-Mallows index, are often used to evaluate the performance of machine learning models, in particular, when facing imbalanced datasets that contain more samples of one class than the other. Recent optimal decision tree algorithms have shown remarkable progress in producing trees that are optimal with respect to linear

    更新日期:2020-09-16
  • Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture for Scene Segmentation
    arXiv.cs.AI Pub Date : 2020-09-15
    Soham Chattopadhyay; Hritam Basak

    Despite the growing success of Convolution neural networks (CNN) in the recent past in the task of scene segmentation, the standard models lack some of the important features that might result in sub-optimal segmentation outputs. The widely used encoder-decoder architecture extracts and uses several redundant and low-level features at different steps and different scales. Also, these networks fail

    更新日期:2020-09-16
  • A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes
    arXiv.cs.AI Pub Date : 2020-09-15
    Yuxin Ma; Arlen Fan; Jingrui He; Arun Reddy Nelakurthi; Ross Maciejewski

    Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in reusing existing labels from similar application domains. Transfer Learning is intended to relax this assumption by modeling relationships between domains, and is

    更新日期:2020-09-16
  • Structural time series grammar over variable blocks
    arXiv.cs.AI Pub Date : 2020-09-15
    David Rushing Dewhurst

    A structural time series model additively decomposes into generative, semantically-meaningful components, each of which depends on a vector of parameters. We demonstrate that considering each generative component together with its vector of parameters as a single latent structural time series node can simplify reasoning about collections of structural time series components. We then introduce a formal

    更新日期:2020-09-16
Contents have been reproduced by permission of the publishers.
导出
全部期刊列表>>
《自然》编辑与您分享如何成为优质审稿人-信息流
物理学研究前沿热点精选期刊推荐
科研绘图
欢迎报名注册2020量子在线大会
化学领域亟待解决的问题
材料学研究精选新
GIANT
自然职场线上招聘会
ACS ES&T Engineering
ACS ES&T Water
屿渡论文,编辑服务
阿拉丁试剂right
张晓晨
田蕾蕾
李闯创
刘天飞
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
天合科研
x-mol收录
X-MOL
清华大学
廖矿标
陈永胜
试剂库存
down
wechat
bug