检索结果-内蒙古大学图书馆

Learning Physical Graph Representations from Visual Scenes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bear, Daniel M. Fan, Chaofei Mrowca, Damian Li, Yunzhu Alter, Seth Nayebi, Aran Schwartz, Jeremy Fei-Fei, Li Wu, Jiajun Tenenbaum, Joshua B. Yamins, Daniel L.K. Department of Psychology Stanford University United States Department of Computer Science Stanford University United States Wu Tsai Neurosciences Institute Stanford University United States MIT CSAIL MIT Brain and Cognitive Sciences Neurosciences Ph.D. Program Stanford University United States

Convolutional Neural Networks (CNNs) have proved exceptional at learning representations for visual object categorization. However, CNNs do not explicitly encode objects, parts, and their physical properties, which has limited CNNs’ success on tasks that require structured understanding of visual scenes. To overcome these limitations, we introduce the idea of "Physical Scene Graphs" (PSGs), which represent scenes as hierarchical graphs, with nodes in the hierarchy corresponding intuitively to object parts at different scales, and edges to physical connections between parts. Bound to each node is a vector of latent attributes that intuitively represent object properties such as surface shape and texture. We also describe PSGNet, a network architecture that learns to extract PSGs by reconstructing scenes through a PSG-structured bottleneck. PSGNet augments standard CNNs by including: recurrent feedback connections to combine low and high-level image information;graph pooling and vectorization operations that convert spatially-uniform feature maps into object-centric graph structures;and perceptual grouping principles to encourage the identification of meaningful scene elements. We show that PSGNet outperforms alternative self-supervised scene representation algorithms at scene segmentation tasks, especially on complex real-world images, and generalizes well to unseen object types and scene arrangements. PSGNet is also able learn from physical motion, enhancing scene estimates even for static images. We present a series of ablation studies illustrating the importance of each component of the PSGNet architecture, analyses showing that learned latent attributes capture intuitive scene properties, and illustrate the use of PSGs for compositional scene inference. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

Grammatical Error Correction as GAN-like sequence labeling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Parnow, Kevin Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

In Grammatical Error Correction (GEC), sequence labeling models enjoy fast inference compared to sequence-to-sequence models;however, inference in sequence labeling GEC models is an iterative process, as sentences are passed to the model for multiple rounds of correction, which exposes the model to sentences with progressively fewer errors at each round. Traditional GEC models learn from sentences with fixed error rates. Coupling this with the iterative correction process causes a mismatch between training and inference that affects final performance. In order to address this mismatch, we propose a GAN-like sequence labeling model, which consists of a grammatical error detector as a discriminator and a grammatical error labeler with Gumbel-Softmax sampling as a generator. By sampling from real error distributions, our errors are more genuine compared to traditional synthesized GEC errors, thus alleviating the aforementioned mismatch and allowing for better training. Our results on several evaluation benchmarks demonstrate that our proposed approach is effective and improves the previous state-of-the-art baseline. Copyright © 2021, The Authors. All rights reserved.

关键词： Error correction

Impact of fabrication methods on binder distribution and charge transport in composite cathodes of all-solid-state batteries

学校读者我要写书评

暂无评论

材料展望（英文）

材料展望（英文） 2023年第4期 121-129页

作者： Benjamin Emley Chaoshan Wu Lihong Zhao Qing Ai Yanliang Liang Zhaoyang Chen Liqun Guo Tanguy Terlier Jun Lou Zheng Fan Yan Yao Materials Science and Engineering Program and Texas Center for Superconductivity at the University of Houston University of Houston4726 Calhoun RdHoustonTX 77204United States of America Materials Science and Engineering Program and Texas Center for Superconductivity at the University of Houston University of Houston4726 Calhoun RdHoustonTX 77204United States of America Department of Electrical and Computer Engineering University of Houston4726 Calhoun RdHoustonTX 77204United States of America Department of Materials Science and Nano Engineering Rice University6100 Main StreetHoustonTX 77005United States of America SIMS Laboratory Shared Equipment AuthorityRice UniversityHoustonTX 77005United States of America Department of Engineering Technology University of HoustonHoustonTX 77204United States of America

The manufacturing process of all-solid-state batteries necessitates the use of polymer ***,these binders,being ionic insulators by nature,can adversely affect charge transport within composite cathodes,thereby impacting the rate performance of the *** this work,we aim to investigate the impact of fabrication methods,specifically the solvent-free dry process versus the slurry-cast wet process,on binder distribution and charge transport in composite cathodes of solid-state *** the dry process,the binder forms a fibrous network,while the wet process results in binder coverage on the surface of cathode active *** difference in microstructure leads to a notable 20-fold increase in ionic conductivity in the dry-processed ***,the cells processed via the dry method exhibit higher capacity retention of 89％and 83％at C/3 and C/2 rates,respectively,in comparison to 68％and 58％for the wet-processed cells at the same *** findings provide valuable insights into the influence of fabrication methods on binder distribution and charge transport,contributing to a better understanding of the binder's role in manufacturing of all-solid-state batteries.

关键词： solid-state battery solvent-free dry process polymer binder lithium thiophosphate electrolyte

Enhancing Pre-trained Language Model with Lexical Simplification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bao, Rongzhou Wang, Jiayi Zhang, Zhuosheng Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple alternatives, lexical simplification (LS) is a recognized method to reduce such lexical diversity, and therefore to improve the understandability of sentences. In this paper, we leverage LS and propose a novel approach which can effectively improve the performance of PrLMs in text classification. A rule-based simplification process is applied to a given sentence. PrLMs are encouraged to predict the real label of the given sentence with auxiliary inputs from the simplified version. Using strong PrLMs (BERT and ELECTRA) as baselines, our approach can still further improve the performance in various text classification tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kim, Nayeon Piao, Yinhua Kim, Sun Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Computer Science and Engineering Seoul National University Korea Republic of Institute of Computer Technology Seoul National University Korea Republic of AIGENDRUG Co. Ltd Korea Republic of

Leveraging knowledge from electronic health records (EHRs) to predict a patient’s condition is essential to the effective delivery of appropriate care. Clinical notes of patient EHRs contain valuable information from healthcare professionals, but have been underused due to their difficult contents and complex hierarchies. Recently, hypergraph-based methods have been proposed for document classifications. Directly adopting existing hypergraph methods on clinical notes cannot sufficiently utilize the hierarchy information of the patient, which can degrade clinical semantic information by (1) frequent neutral words and (2) hierarchies with imbalanced distribution. Thus, we propose a taxonomy-aware multi-level hypergraph neural network (TM-HGNN), where multi-level hypergraphs assemble useful neutral words with rare keywords via note and taxonomy level hyperedges to retain the clinical semantic information. The constructed patient hypergraphs are fed into hierarchical message passing layers for learning more balanced multi-level knowledge at the note and taxonomy levels. We validate the effectiveness of TM-HGNN by conducting extensive experiments with MIMIC-III dataset on benchmark in-hospital-mortality prediction. Copyright © 2023, The Authors. All rights reserved.

关键词： Taxonomies

Novel action of biphasic electric current in vitro osteogenesis of human bone marrow mesenchymal stromal cells coupled with VEGF production

学校读者我要写书评

暂无评论

Novel action of biphasic electric current in vitro osteogene...

International Conference on Osteoporosis and Bone Research 2008(2008国际骨质疏松和骨矿疾病学术会议)

作者： In Sook Kim JongKeun Song Yun MiSong Tae Hyung Lee Tae Hyung Cho Shin Saeng Lim Hui Pan Sung June Kim Soon Jung Hwang Dental Research Institute Seoul National UniversityBrain Korea 21 2nd Program for Craniomaxillofacial Life ScienceKorea School of Electrical Engineering and Computer ScienceSeoul National UniversitySeoulKorea Department of Maxillofacial Cell and Developmental BiologyDepartment of Oral and Maxillofacial SurgerySchool of DentistrySeoul National UniversityBrain Korea 21 2nd Program for Craniomaxillofacial Life ScienceSeoulKorea

Prosody dependent speech recognition on radio news corpus of American English

学校读者我要写书评

暂无评论

Prosody dependent speech recognition on radio news corpus of...

作者： Chen, Ken Hasegawa-Johnson, Mark Cohen, Aaron Borys, Sarah Kim, Sung-Suk Cole, Jennifer Choi, Jeung-Yoon IEEE Beckman Institute University of Illinois Urbana IL 61801 United States Department of Chemistry and Biochemistry University of California San Diego Phi Kappa Phi IEEE Signal Processing Society Acoustical Society of America Audio Engineering Society International Speech Communication Association Eta Kappa Nu Tau Beta Pi Sigma Xi School of Computer and Information Yong-In University Yongin Korea Republic of Linguistics and Comouter Science University of Illinois Urbana-Champaign Cognitive Science Group Beckman Institute University of Illinois Linguistic Society of America International Phonetic Society Phi Beta Kappa University of Illinois Urbana-Champaign

Does prosody help word recognition? This paper proposes a novel probabilistic framework in which word and phoneme are dependent on prosody in a way that reduces word error rates (WER) relative to a prosody-independent recognizer with comparable parameter count. In the proposed prosody-dependent speech recognizer, word and phoneme models are conditioned on two important prosodic variables: the intonational phrase boundary and the pitch accent. An information-theoretic analysis is provided to show that prosody dependent acoustic and language modeling can increase the mutual information between the true word hypothesis and the acoustic observation by exciting the interaction between prosody dependent acoustic model and prosody dependent language model. Empirically, results indicate that the influence of these prosodic variables on allophonic models are mainly restricted to a small subset of distributions: the duration PDFs (modeled using an explicit duration hidden Markov model or EDHMM) and the acoustic-prosodic observation PDFs (normalized pitch frequency). Influence of prosody on cepstral features is limited to a subset of phonemes: for example, vowels may be influenced by both accent and phrase position, but phrase-initial and phrase-final consonants are independent of accent. Leveraging these results, effective prosody dependent allophonic models are built with minimal increase in parameter count. These prosody dependent speech recognizers are able to reduce word error rates by up to 11 % relative to prosody independent recognizers with comparable parameter count, in experiments based on the prosodically-transcribed Boston Radio News corpus. © 2006 IEEE.

关键词： Speech recognition

3-Dimensional Kinematic Comparison of Arm Movements between an Individual with NGLY1 Deficiency and a Neurotypical Individual

学校读者我要写书评

暂无评论

Case Reports in Clinical Medicine 2024年第4期13卷 122-146页

作者： Charles S. Layne Christopher A. Malaya Brock Futrell Dacia Martinez Diaz Christian Alfaro Hannah E. Gustafson Subhalakshmi Chandrasekaran Rhea M. Phatak Bernhard Suter Department of Health and Human Performance University of Houston Houston TX USA Center for Neuromotor and Biomechanics Research University of Houston Houston TX USA Center for Neuro Engineering and Cognitive Science University of Houston Houston TX USA Department of Computer Science and Engineering Texas A&M University College Station TX USA Blue Bird Circle Rett Center Texas Children&#8217s Hospital Houston TX USA Baylor College of Medicine Houston TX USA

NGLY1 Deficiency is an ultra-rare autosomal recessively inherited disorder. Characteristic symptoms include among others, developmental delays, movement disorders, liver function abnormalities, seizures, and problems with tear formation. Movements are hyperkinetic and may include dysmetric, choreo-athetoid, myoclonic and dystonic movement elements. To date, there have been no quantitative reports describing arm movements of individuals with NGLY1 Deficiency. This report provides quantitative information about a series of arm movements performed by an individual with NGLY1 Deficiency and an aged-matched neurotypical participant. Three categories of arm movements were tested: 1) open ended reaches without specific end point targets;2) goal-directed reaches that included grasping an object;3) picking up small objects from a table placed in front of the participants. Arm movement kinematics were obtained with a camera-based motion analysis system and “initiation” and “maintenance” phases were identified for each movement. The combination of the two phases was labeled as a “complete” movement. Three-dimensional analysis techniques were used to quantify the movements and included hand trajectory pathlength, joint motion area, as well as hand trajectory and joint jerk cost. These techniques were required to fully characterize the movements because the NGLY1 individual was unable to perform movements only in the primary plane of progression instead producing motion across all three planes of movement. The individual with NGLY1 Deficiency was unable to pick up objects from a table or effectively complete movements requiring crossing the midline. The successfully completed movements were analyzed using the above techniques and the results of the two participants were compared statistically. Almost all comparisons revealed significant differences between the two participants, with a notable exception of the 3D initiation area as a percentage of the complete movement. The stati

关键词： NGLY1 Deficiency Developmental Disorders Kinematics 3 Dimensional Analyses

Symmetry-protected mode coupling near normal incidence for narrow-band transmission filtering in a dielectric grating

学校读者我要写书评

暂无评论

Physical Review B 2014年第16期89卷 165111-165111页

作者： J. M. Foley S. M. Young J. D. Phillips Applied Physics Program University of Michigan Ann Arbor Michigan 48109 USA Electrical Engineering and Computer Science Department University of Michigan Ann Arbor Michigan 48109 USA Physics Department University of Michigan Ann Arbor Michigan 48109 USA

A narrow-band transmission filter is demonstrated near normal incidence that operates through relaxation of supported-mode selection rules and is explained in the context of group theory. We calculated the transverse magnetic and transverse electric dispersion relations of a dielectric grating in the subwavelength and near-wavelength region using finite element modal analysis and determine the modes' corresponding irreducible representations. Coupling to select transverse magnetic modes at normal incidence is optimized to yield broadband high reflectance that acts as the background for the transmission filter. While some modes couple at normal incidence, others are shown to remain inaccessible due to symmetry mismatch. Away from normal incidence, the reduced symmetry relaxes the selection rules, enabling weak coupling between the incident field and these symmetry-protected modes. This weak coupling produces narrow transmission bands within the opaque background. Furthermore, by choosing the plane of incidence to include or exclude the grating periodicity, we show that orthogonal mode sets can independently be selected to couple to the incident light, yielding separate transmission bands. This spectral filtering is experimentally demonstrated with a suspended silicon grating in the infrared spectrum (7–14μm), which agrees well with simulated transmittance spectra and modal analysis.

关键词： GROUP theory MODAL analysis DIELECTRICS SYMMETRIC functions FINITE element method