Главная    Ex Libris    Книги    Журналы    Статьи    Серии    Каталог    Wanted    Загрузка    ХудЛит    Справка    Поиск по индексам    Поиск    Форум   
blank
Авторизация

       
blank
Поиск по указателям

blank
blank
blank
Красота
blank
Krose B., van der Smagt P. — An introduction to neural networks
Krose B., van der Smagt P. — An introduction to neural networks

Читать книгу
бесплатно

Скачать книгу с нашего сайта нельзя

Обсудите книгу на научном форуме



Нашли опечатку?
Выделите ее мышкой и нажмите Ctrl+Enter


Название: An introduction to neural networks

Авторы: Krose B., van der Smagt P.

Аннотация:

The term neural network was traditionally used to refer to a network or circuit of biological neurons.[1] The modern usage of the term often refers to artificial neural networks, which are composed of artificial neurons or nodes. Thus the term may refer to either biological neural networks are made up of real biological neurons or artificial neural networks for solving artificial intelligence problems.
Unlike von Neumann model computations, artificial neural networks do not separate memory and processing and operate via the flow of signals through the net connections, somewhat akin to biological networks.
These artificial networks may be used for predictive modeling, adaptive control and applications where they can be trained via a dataset.


Язык: en

Рубрика: Computer science/

Статус предметного указателя: Готов указатель с номерами страниц

ed2k: ed2k stats

Издание: 8-th edition

Год издания: 1996

Количество страниц: 135

Добавлена в каталог: 11.04.2013

Операции: Положить на полку | Скопировать ссылку для форума | Скопировать ID
blank
Предметный указатель
$k$-means clustering      61
ACE      77
Activation function      17 19
Activation function, hard limiting      17
Activation function, Heaviside      23
Activation function, linear      17
Activation function, nonlinear      33
Activation function, semi-linear      17
Activation function, sgn      23
Activation function, sigmoid      17 36 39
Activation function, sigmoid, derivative of      36
Activation function, threshold      51
ADALINE      18 23 27
Adaline, vision      97
Adaptive critic element      77
Analogue implementation      115-117
annealing      54
ART      57 69 109
ASE      77
ASE, activation function      77
ASE, bias      77
Associative learning      18
Associative memory      52
Associative memory, instability of stored patterns      52
Associative memory, spurious stable states      52
Associative search element      77
Asymmetric divergence      55
Asynchronous update      16 50
Auto-associator      50
Auto-associator, vision      99
Back-propagation      33 39 45 109 116
Back-propagation, advanced training algorithms      40
Back-propagation, conjugate gradient      40
Back-propagation, derivation of      34
Back-propagation, discovery of      13
Back-propagation, gradient descent      34 37 40
Back-propagation, implementation on Connection Machine      113
Back-propagation, learning by pattern      37
Back-propagation, learning rate      37
Back-propagation, local minima      40
Back-propagation, momentum      37
Back-propagation, network paralysis      39
Back-propagation, oscillation in      37
Back-propagation, understanding      35
Back-propagation, vision      99
Bias      19
Bio-chips      115
Bipolar cells, retina      118
Bipolar cells, silicon retina      119
Boltzmann distribution      54
Boltzmann machine      54 116
Carnegie Mellon University      114
CART      63
Cart-pole      79
Chemical implementation      115
Cluster      61
Clustering      57
Coarse-grain parallelism      111
Coding, lossless      98
Coding, lossy      98
Cognitron      57 100
Competitive learning      57
Competitive learning, error-function      60
Competitive learning, frequency sensitive      60
Conjugate directions      41
Conjugate gradient      40
Connection Machine      109 111-113
Connection Machine, architecture      112
Connection Machine, communication      112
Connection Machine, NEWS grid      112
Connection Machine, nexus      112
Connectionist Models      13
Connectivity, constraints      115
Connectivity, optical      116
Convergence, steepest descent      41
Cooperative algorithm      104
Correlation matrix      68
Counterpropagation      62
Counterpropagation network      63
DARPA neural network study      9
Decoder      78
Deflation      69
Delta rule      18 27-29
Delta rule, generalised      33 35
Digital implementation      115
Dimensionality reduction      57
Discovery vs. creation      13
Discriminant analysis      64
Distance measure      60
Dynamic programming      77
Dynamics, in neural networks      17
Dynamics, robotics      86 92
EEPROM      117
Eigenvector transformation      67
Eligibility      78
Elman network      48-50
Emulation      109 111
Energy      19
Energy, Hopfield network      51f.
Energy, travelling salesman problem      53
EPROM      117
Error      19
Error measure      43
Error, back-propagation      34
Error, competitive learning      60
Error, learning      43
Error, perceptron      28
Error, quadratic      34
Error, test      43
Excitation      16
External input      20
eye      69
Face recognition      99
Feature extraction      57 99
Feed-forward network      17 20 33 35 42 45
FET      118
Fine-grain parallelism      111
FORGY      61
Forward kinematics      85
Gaussian      91
General learning      87
Generalised Delta Rule      33 35
Gradient descent      28 34 37 40
Granularity of parallelism      111
Hard limiting activation function      17
Heaviside      23
Hebb rule      18 25 52 67 121
Hebb rule, normalised      67
hessian      41
High level vision      97
Holographic correlators      116
Hopfield network      50 94 119
Hopfield network, as associative memory      52
Hopfield network, as associative memory, instability of stored patterns      52
Hopfield network, as associative memory, spurious stable states      52
Hopfield network, energy      51f.
Hopfield network, graded response neurons      52
Hopfield network, optimisation      53
Hopfield network, stable limit points      51
Hopfield network, stable neuron in      51
Hopfield network, stable pattern in      51
Hopfield network, stable state in      51
Hopfield network, stable storage algorithm      52
Hopfield network, stochastic update      54
Hopfield network, symmetry      52
Hopfield network, un-learning      52
Horizontal cells, retina      118
Horizontal cells, silicon retina      119
Image compression      98
Image compression, back-propagation      99
Image compression, PCA      99
Image compression, self-organising networks      98
implementation      109
Implementation, analogue      115-117
Implementation, chemical      115
Implementation, connectivity constraints      115
Implementation, digital      115
Implementation, on Connection Machine      113
Implementation, optical      115
Implementation, silicon retina      119
Indirect learning      87
Information gathering      15
Inhibition      16
Instability of stored patterns      52
Intermediate level vision      97
Inverse kinematics      85
Ising spin model      50
ISODATA      61
Jacobian matrix      88 90
Jordan network      48
Kirchoff laws      116
KISS      90
Kohonen network      64 119
Kohonen network, 3-dimensional      90
Kohonen network, for robot control      90
Kullback information      55
Leaky learning      60
Learning      18 20 117
Learning error      43
Learning rate      18
Learning rate, back-propagation      37
Learning vector quantisation      64
Learning, associative      18
Learning, general      87
Learning, indirect      87
Learning, LNeuro      121
Learning, self-supervised      18 87
Learning, specialised      88
Learning, supervised      18
Learning, unsupervised      18 87
LEP      119
Linear activation function      17
Linear convergence      41
Linear discriminant function      24
Linear networks      28
Linear networks, vision      99
Linear threshold element      26
LNeuro      119
LNeuro, activation function      121
LNeuro, ALU      120
LNeuro, learning      121
LNeuro, RAM      120
Local minima, back-propagation      40
Look-up table      16 63
Lossless coding      98
Lossy coding      98
Low level vision      97
LVQtwo      64
Markov random field      105
MARS      63
Mean vector      68
MIMD      111
MIT      112
Mobile robots      94
Momentum      37
Multi-layer perceptron      54
Neocognitron      98 100
Nestor      109
NETtalk      45
Network paralysis, back-propagation      39
NeuralWare      109
Neuro-computers      115
Nexus      112
Non-cooperative algorithm      104
Normalisation      67
Notation      19
Octree methods      63
Offset      20
Oja learning rule      68
Optical implementation      115
Optimisation      53
Oscillation in back-propagation      37
Output vs. activation of a unit      19
Panther, hiding      69
Panther, resting      69
Parallel distributed processing      13 15
Parallelism, coarse-grain      111
Parallelism, fine-grain      111
PCA      66
PCA, image compression      99
PDP      13 15
Perceptron      13 18 23 26 29 31
Perceptron, Convergence Theorem      24
Perceptron, error      28
Perceptron, learning rule      24
Perceptron, threshold      25
Perceptron, vision      97
Photo-receptor, retina      118
Photo-receptor, silicon retina      118
Positive definite      41
Principal components      66
PROM      117
Prototype vectors      66
PYGMALION      109
RAM      109 117
Recurrent networks      17 47
Recurrent networks, Elman network      48-50
Recurrent networks, Jordan network      48
Reinforcement learning      75
Relaxation      17
Representation      20
Representation vs. learning      20
resistor      116
retina      98
Retina, bipolar cells      118
Retina, horizontal cells      118
Retina, photo-receptor      118
Retina, retinal ganglion      118
Retina, structure      118
Retina, triad synapses      118
Retinal ganglion      118
Robotics      85
Robotics, dynamics      86 92
Robotics, forward kinematics      85
Robotics, inverse kinematics      85
Robotics, trajectory generation      86
Rochester Connectionist Simulator      109
ROM      117
Self-organisation      18 57
Self-organising networks      57
Self-organising networks, image compression      98
Self-organising networks, vision      98
Self-supervised learning      18 87
Semi-linear activation function      17
Sgn function      23
Sigma unit      16
Sigma-pi unit      16
Sigmoid activation function      17 36 39
Sigmoid activation function, derivative of      36
Silicon retina      105 117
Silicon retina, bipolar cells      119
Silicon retina, horizontal cells      119
Silicon retina, implementation      119
Silicon retina, photo-receptor      118
SIMD      111f.
Simulated annealing      54
Simulation      109
Simulation, taxonomy      109
Specialised learning      88
Spurious stable states      52
1 2
blank
Реклама
blank
blank
HR
@Mail.ru
       © Электронная библиотека попечительского совета мехмата МГУ, 2004-2017
Электронная библиотека мехмата МГУ | Valid HTML 4.01! | Valid CSS! О проекте