Материал: искусственный интеллект

Внимание! Если размещение файла нарушает Ваши авторские права, то обязательно сообщите нам

suai.ru/our-contacts

Index

query, 3, 84 QWeb, 2

relevance and information need, 3 user/item embedding, 84

Information retrieving approach, 35 Interference contribution, 7 Interference effects, 17, 20, 21 Interference plus context effect, 28Ð30 Irreducible quantum randomness, 65

K

Ket-and Bra-vectors, 73Ð74

Ket vectors, one-qubit-vectors, 121 Kolmogorov probability space, 53 KolmogorovÕs axiomatics

σ -algebra, 53 Bayes formula, 55

Bayesian inference, 55 Borel σ -algebra, 53 discrete random variable, 55 Ω elementary events, 53 experimental contexts, 53 FTP, 55

Kolmogorov probability space, 53 observables, 53

probability distribution, 54 probability measure, 53Ð54 transition probabilities, 55

Kolmogorov theory, 43Ð44

L

Latent Dirichlet Allocation (LDA), 84, 164 Latent semantic analysis (LSA), 84, 164 Linguistically enhanced word embedding,

99Ð100

Logic-based weighting, 137Ð140

M

Machine learning paradigms, 35

Maximum likelihood estimation (MLE), 152 Meaning bond concept, 30Ð32

Meet and join operators bi-dimensional subspace, rays, 154 deÞnition, 153

intersection and union of sets, 154 one-dimensional subspace, planes, 154 See also Query-by-theme language (QTL)

Meta embedding, 100

N

Named Entity Recognition (NER), 91

Neural Network Language Model (NNLM), 87

quantum machine learning

171

Non-commutativity, 62

Non-negative matrix factorization (NMF), 160

O

Out-Of-Vocabulary (OOV) Problem, 98

OWA approach, 141

P

Part-Of-Speech (POS) tagging, 91 Point-wise Mutual Information (PMI) matrix,

102 Poly-representation, 164 Polysemy problem, 98

Positive operator valued measures (POVMs), 67

Probabilistic models, 152Ð153 Pseudo relevance feedback (PRF), 163

Q

Quantum-based data type constructors set data, 125Ð126

tuple, 123Ð125

Quantum Bayesianism (QBism), 65 Quantum cognition, 27

Quantum cognitive science, 36

Quantum conditional (transition) probability, 65Ð66

Quantum entanglement, 39 Quantum formalism, 36 Quantum interference effect, 36 Quantum mathematics

Hermitian operators, Hilbert space, 56Ð58 normalized vectors and density operators,

58Ð59 Quantum mechanics (QM)

Boolean logics, 52 BornÕs rule, 60Ð61

Copenhagen interpretation, 64Ð65 ensemble interpretation, 64 Hermitian operators, 52 information interpretations, 65 Ket-and Bra-vectors, 73Ð74 logic, 70Ð71

mathematical description physical observables, 60 quantum states, 59Ð60

non-physicists, 51

probability calculus, linear algebra and logic, 115

projection postulate, 52 qubit space, 74Ð75

separable and non-separable entanglement, 75Ð76

suai.ru/our-contacts

172

Quantum mechanics (QM) (cont.) spectral, 60

square integrable functions, 71 statistical theory, 51Ð52

tensor product operation, 72Ð73 time evolution, wave function, 61 two-slit experiment, 76Ð79

See also KolmogorovÕs axiomatics Quantum probability theory

human judgments, 43

Kolmogorov concept, random variable, 43Ð44

logical, vector space and probabilistic approach, 43

Quantum Query Language (QQL), 164

Quantum state tomography, 27 Quantum structures

abstractness and concreteness, 4 human culture, 5, 6

meaning and concept, 3Ð4 physical objects, 5

See also Double-slit experiment Quantum Web (QWeb)

composite entity, 16 concepts, 17Ð19 deÞned, 2

documental entities, 14 interference effects, 20 interrogative process, 14 measurements, 15 n-dimensional Hilbert space, 16 uniform meaning connection, 16 VSM, 15Ð16

webpages, 15 Qubit space, 74Ð75

Query-by-theme language (QTL) document ranking, 156Ð158 features and terms, 155Ð156 JOIN function, 161

meet and join operators, 158Ð160 MEET function, 162

NMF, 160 notations, 155

one-and bi-dimensional themes, 161 themes, 156

Query expansion (QE), 162, 164 Question answering, 94

R

Reading Comprehension (RC) task, 92

Relevance feedback (RF), 162Ð163

quantum machine learning

Index

S

Schmidt orthogonalization algorithm, 38 Set data type constructor, 125Ð126

Sets vs. vector spaces, 147Ð148 Sentence classiÞcation, 90Ð91 Sentence-level applications

classiÞcation, 89, 90 document-level representation, 92 sentence classiÞcation, 90Ð91 sequential labeling, 91Ð92

Sentence-pair level application question answering, 94 RC task, 92

sentence-pair vs. sentence based task, 92, 93

Seq2seq application, 94Ð95 Sequential labeling, 91Ð92

Singular Value Decomposition (SVD), 84, 164 Skip-gram, 87, 88

SQuAD dataset, 94

Square-rooted positive semi-deÞniteness, 119 Sub-word embedding, 100

T

Tensor product operation, 72Ð73

Term Relevance Weight (TRW) function, 152 Thematic modeling, 35

Topic model, 101 Transition probabilities, 55

degenerate spectra and POVMs, 67 doubly stochastic, 67 nondegenerate observables, 66

Tuple data type constructor, 123Ð125 Two-slit experiment, QM, 76Ð79

U

Unit interval, 119

User and smart information system, 36

V

VŠxjš interpretation, 68Ð70 Vector-space based approach

contextual windows, 102Ð103

topic distribution derivation, 101Ð102 Vector space model (VSM), 15Ð16, 150Ð152 Vector spaces

basis and dimension, 147 deÞnition, 147

linear independence, 147 vs. sets, 147Ð148

suai.ru/our-contacts

Index

W

Weighted sum, 141 Weighting formula

arithmetic formula on operands, 141 atomic conditions, 130, 131 contributions, 130

database condition, 131 FaginÕs approach, 140

logic-based weighting approach on min/max, 141

OWA approach, 141 proximity condition, 131 query language, 130

summer cottages and weighted condition tree, 131, 132

text retrieval, 131 types, 140 weighted sum, 141

Word co-occurrence, 20, 21, 25 Word embedding

advanced word embedding, 100 categories, 84

CBOW, 88 contextualized, 99 CV and NLP, 85 C&W, 87 description, 84

quantum machine learning

173

distributional hypothesis, 86Ð87 evaluations

downstream task, 96Ð97 word property, 95Ð96

Glove, 89 ÒinterpretabilityÓ, 99 limitations

distributional hypothesis, 98 lack of theoretical explanation,

98

OOV problem, 98 polysemy problem, 98

semantic change over time, 98 linguistically enhanced, 99Ð100 LSA, 84

NNLM, 87

sentence-level applications, 89Ð92 sentence-pair level application, 92Ð94 Seq2seq application, 94Ð95 Skip-gram, 87, 88

sub-word embedding, 100 towards dynamic version, 103Ð106

visualization of selected words, 85, 86 word-level applications, 89

See also Vector-space based approach Word-level applications, 89

Word representation, 104

suai.ru/our-contacts

quantum machine learning

Bob Coecke

Ariane Lambert-Mogiliansky (Eds.)

LNCS 11690

Quantum Interaction

11th International Conference, QI 2018

Nice, France, September 3–5, 2018

Revised Selected Papers

suai.ru/our-contacts

quantum machine learning

Lecture Notes in Computer Science

11690

Founding Editors

Gerhard Goos

Karlsruhe Institute of Technology, Karlsruhe, Germany

Juris Hartmanis

Cornell University, Ithaca, NY, USA

Editorial Board Members

Elisa Bertino

Purdue University, West Lafayette, IN, USA

Wen Gao

Peking University, Beijing, China

Bernhard Steffen

TU Dortmund University, Dortmund, Germany

Gerhard Woeginger

RWTH Aachen, Aachen, Germany

Moti Yung

Columbia University, New York, NY, USA