|
|
 |
| Авторизация |
|
|
|
| Поиск по указателям |
|
|
|
|
|
|
|
 |
|
|
|
| Krose B., van der Smagt P. — An introduction to neural networks |
|
|
|
| Предметный указатель |
 -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
|
|
|
| Реклама |
|
|
|
|
|
О проекте