Filters








51,932 Hits in 6.7 sec

Near optimal hierarchical encoding of types [chapter]

Andreas Krall, Jan Vitek, R. Nigel Horspool
1997 Lecture Notes in Computer Science  
We present a new algorithm based on graph coloring which computes a near optimal hierarchical encoding of type hierarchies.  ...  There are well-known methods for performing fast constant time type inclusion tests that use a hierarchical bit vector encoding of the partial ordered set representing the type hierarchy.  ...  The We have presented a near optimal algorithm for nding hierarchical encodings for type hierarchies.  ... 
doi:10.1007/bfb0053377 fatcat:gggxpabs6bfh3hpypxcbziv3em

Breast Cancer Detection Using Hierarchical B-Spline Networks [chapter]

Yuehui Chen, Mingjun Liu, Bo Yang
2006 Lecture Notes in Computer Science  
In this paper, an optimized hierarchical B-spline network was employed to detect the breast cancel.  ...  For evolving a hierarchical B-spline network model, a tree-structure based evolutionary algorithm and the Particle Swarm Optimization (PSO) are used to find an optimal detection model.  ...  Acknowledgement This research was partially supported the Natural Science Foundation of China under contract number 60573065, and The Provincial Science and Technology Development Program of Shandong under  ... 
doi:10.1007/11881070_4 fatcat:w2jpju7kwfhepgpkh6i3o7orhm

Efficient type inclusion tests

Jan Vitek, R. Nigel Horspool, Andreas Krall
1997 Proceedings of the 12th ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications - OOPSLA '97  
A type inclusion test determines whether one type is a subtype of another. Efficient type testing techniques exist for single subtyping, but not for languages with multiple subtyping.  ...  In this paper, we present three new encodings of the subtype relation, the packed encoding, the bit-packed encoding and the compact encoding. These encodings have different characteristics.  ...  of alternative techniques and uses of type inclusion tests; and the OOPSLA reviewers as their technical comments helped us improve this paper.  ... 
doi:10.1145/263698.263730 dblp:conf/oopsla/VitekHK97 fatcat:7q3f47iiercmngj4boaqglo6ma

Efficient type inclusion tests

Jan Vitek, R. Nigel Horspool, Andreas Krall
1997 SIGPLAN notices  
A type inclusion test determines whether one type is a subtype of another. Efficient type testing techniques exist for single subtyping, but not for languages with multiple subtyping.  ...  In this paper, we present three new encodings of the subtype relation, the packed encoding, the bit-packed encoding and the compact encoding. These encodings have different characteristics.  ...  of alternative techniques and uses of type inclusion tests; and the OOPSLA reviewers as their technical comments helped us improve this paper.  ... 
doi:10.1145/263700.263730 fatcat:dbivimmkbvet3i2oe77lcyorfi

Near-lossless image compression using an improved edge adaptive hierarchical interpolation

Yenewondim Biadgie Sinshahw
2020 Indonesian Journal of Electrical Engineering and Computer Science  
In the previous work, an edge adaptive hierarchical interpolation (EAHINT) was proposed for resolution scalable lossless compression of images.  ...  Instead of thinking lossless or lossy image compression methods, near-loss image compression mehod can be used to compromise the two conflicting requirements.  ...  In section 3, an overview of the improved edge adaptive hierarchical interpolation (I-EAHINT) for progressive near-lossless image encoding is described.  ... 
doi:10.11591/ijeecs.v20.i3.pp1576-1583 fatcat:2kbfucmtzbhlroawtjztzpbsfy

Evolving Hierarchical RBF Neural Networks for Breast Cancer Detection [chapter]

Yuehui Chen, Yan Wang, Bo Yang
2006 Lecture Notes in Computer Science  
Hierarchical RBF networks consist of multiple RBF networks assembled in different level or cascade architecture.  ...  For evolving a hierarchical RBF network model, Extended Compact Genetic Programming (ECGP), a tree-structure based evolutionary algorithm and the Differential Evolution (DE) are used to find an optimal  ...  Acknowledgment This research was partially supported the Natural Science Foundation of China under contract number 60573065, and The Provincial Science and Technology Development Program of Shandong under  ... 
doi:10.1007/11893295_16 fatcat:nve75bfisbdqhmebdkx3ie6pm4

A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization

Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Preksha Nema, Mitesh M. Khapra, Shreyas Shetty
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)  
To this end, we propose a mixed hierarchical attention based encoderdecoder model which is able to leverage the structure in addition to the content of the tables.  ...  In this work, we consider summarizing structured data occurring in the form of tables as they are prevalent across a wide variety of domains.  ...  Also U = (u 1 , u 2 , ...u T ) represents the type of each record where u k is onehot encoding for the record type for record r k .  ... 
doi:10.18653/v1/n18-2098 dblp:conf/naacl/JainLSNKS18 fatcat:6awnfcocjzd3fo7gv6iyck45kq

Fine-Grained Entity Typing in Hyperbolic Space

Federico López, Benjamin Heinzerling, Michael Strube
2019 Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)  
Our analysis suggests that the adequacy of this geometry depends on the granularity of the type inventory and the way hierarchical relations are inferred. 1  ...  We study the ability of hyperbolic embeddings to capture hierarchical relations between mentions in context and their target types in a shared vector space.  ...  This work has been supported by the German Research Foundation (DFG) as part of the Research Training Group Adaptive Preparation of Information from Heterogeneous Sources (AIPHES) under grant No.  ... 
doi:10.18653/v1/w19-4319 dblp:conf/rep4nlp/LopezHS19 fatcat:6qwsmsqsg5galbm3dhyvcetru4

Embedding Text in Hyperbolic Spaces

Bhuwan Dhingra, Christopher Shallue, Mohammad Norouzi, Andrew Dai, George Dahl
2018 Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)  
Natural language text exhibits hierarchical structure in a variety of respects.  ...  The resulting embeddings seem to encode certain intuitive notions of hierarchy, such as wordcontext frequency and phrase constituency.  ...  The resulting embeddings are hierarchically organized such that words occurring in many contexts are placed near the origin and words occurring in few contexts are placed near the boundary of the space  ... 
doi:10.18653/v1/w18-1708 dblp:conf/textgraphs/DhingraSNDD18 fatcat:xmfgkg7jg5fhpnk2qv2zi6wk5q

Embedding Text in Hyperbolic Spaces [article]

Bhuwan Dhingra, Christopher J. Shallue, Mohammad Norouzi, Andrew M. Dai, George E. Dahl
2018 arXiv   pre-print
Natural language text exhibits hierarchical structure in a variety of respects.  ...  The resulting embeddings seem to encode certain intuitive notions of hierarchy, such as word-context frequency and phrase constituency.  ...  The resulting embeddings are hierarchically organized such that words occurring in many contexts are placed near the origin and words occurring in few contexts are placed near the boundary of the space  ... 
arXiv:1806.04313v1 fatcat:nvbydehtqncsbktgi674fqerca

A Mixed Hierarchical Attention based Encoder-Decoder Approach for Standard Table Summarization [article]

Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Preksha Nema, Mitesh M. Khapra, Shreyas Shetty
2018 arXiv   pre-print
To this end, we propose a mixed hierarchical attention based encoder-decoder model which is able to leverage the structure in addition to the content of the tables.  ...  In this work, we consider summarizing structured data occurring in the form of tables as they are prevalent across a wide variety of domains.  ...  Input Encodings: Attributes were encoded based on the attribute type. Numbers are encoded in binary representation. Record type is encoded as a one-hot vector.  ... 
arXiv:1804.07790v1 fatcat:yirexve3lzfi5o2eegzgzh3pui

Improved hierarchial intra prediction based on adaptive interpolation filtering for lossless compression

Li-Li Wang, Wan-Chi Siu
2013 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013)  
The residual block is encoded by rate optimization. Experimental results show that the proposed algorithm can improve the compression efficiency of lossless intra coding.  ...  Specifically, four subblocks are firstly formed by sampling pixels in one macroblock/block, and then a hierarchical intra prediction is performed on these subblocks.  ...  Figs.1-3 show the structures of hierarchical intra prediction for the I8MB type, I16MB type and Chroma blocks, respectively.  ... 
doi:10.1109/iscas.2013.6571833 dblp:conf/iscas/WangS13 fatcat:djnj2da2cver5nw4iqxduezfmi

Natural Language Generation by Hierarchical Decoding with Linguistic Patterns

Shang-Yu Su, Kai-Ling Lo, Yi Ting Yeh, Yun-Nung Chen
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)  
Furthermore, the design of the hierarchical decoding is flexible and easily-extensible in various NLG systems 1 .  ...  scratch by jointly optimizing sentence planning and surface realization using a simple cross entropy loss training criterion.  ...  The authors are supported by the Institute for Information Industry, Ministry of Science and Technology of Taiwan, Google Research, Microsoft Research, and Medi-aTek Inc..  ... 
doi:10.18653/v1/n18-2010 dblp:conf/naacl/SuLYC18 fatcat:6jwzko37prbhbn3snks55verwq

End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression [article]

M.Akın Yılmaz, A.Murat Tekalp
2021 arXiv   pre-print
This paper proposes a learned hierarchical bi-directional video codec (LHBDC) that combines the benefits of hierarchical motion-compensated prediction and end-to-end optimization.  ...  Compared to conventional video codecs, the R-D performance of our end-to-end optimized codec outperforms those of both x265 and SVT-HEVC encoders ("veryslow" preset) in PSNR and MS-SSIM as well as HM 16.23  ...  As a result, the inference process of optimized learned image/video encoders is faster than traditional R-D optimization of image and video encoders.  ... 
arXiv:2112.09529v1 fatcat:auiqvzwpf5bi7nznou4ygducmi

Hierarchical quantum classifiers

Edward Grant, Marcello Benedetti, Shuxiang Cao, Andrew Hallam, Joshua Lockhart, Vid Stojevic, Andrew G. Green, Simone Severini
2018 npj Quantum Information  
Quantum circuits with hierarchical structure have been used to perform binary classification of classical data encoded in a quantum state.  ...  We compare performance for several different parameterizations on two classical machine learning datasets, Iris and MNIST, and on a synthetic dataset of quantum states.  ...  This type of encoding requires N qubits to encode an N dimensional data-vector and, therefore, is less efficient in terms of space.  ... 
doi:10.1038/s41534-018-0116-9 fatcat:xpzvfp5favderpgcwyz5o4zyby
« Previous Showing results 1 — 15 out of 51,932 results