Modeling Brain Function: The World of Attractor Neural NetworksCambridge University Press, 1989 - Всего страниц: 504 One of the most exciting and potentially rewarding areas of scientific research is the study of the principles and mechanisms underlying brain function. It is also of great promise to future generations of computers. A growing group of researchers, adapting knowledge and techniques from a wide range of scientific disciplines, have made substantial progress understanding memory, the learning process, and self organization by studying the properties of models of neural networks - idealized systems containing very large numbers of connected neurons, whose interactions give rise to the special qualities of the brain. This book introduces and explains the techniques brought from physics to the study of neural networks and the insights they have stimulated. It is written at a level accessible to the wide range of researchers working on these problems - statistical physicists, biologists, computer scientists, computer technologists and cognitive psychologists. The author presents a coherent and clear nonmechanical presentation of all the basic ideas and results. More technical aspects are restricted, wherever possible, to special sections and appendices in each chapter. The book is suitable as a text for graduate courses in physics, electrical engineering, computer science and biology. |
Результаты поиска по книге
Результаты 1 – 5 из 79
Стр. vii
... Results . 146 • 146 . . 147 • 150 152 • • • • 153 155 155 4.1.1 Simplifying assumptions and specific questions . 155 4.1.2 Specific answers for low loading of random memories 4.1.3 Properties of the noiseless network 4.1.4 Properties of ...
... Results . 146 • 146 . . 147 • 150 152 • • • • 153 155 155 4.1.1 Simplifying assumptions and specific questions . 155 4.1.2 Specific answers for low loading of random memories 4.1.3 Properties of the noiseless network 4.1.4 Properties of ...
Стр. ix
... results . . . . 6.2 Statistical Estimates of Storage 6.2.1 Statistical signal to noise analysis . . . 262 262 266 • 267 271 271 271 273 275 275 • 278 278 .. 283 6.2.2 Absolute informational bounds on storage capacity 6.2.3 Coupling ...
... results . . . . 6.2 Statistical Estimates of Storage 6.2.1 Statistical signal to noise analysis . . . 262 262 266 • 267 271 271 271 273 275 275 • 278 278 .. 283 6.2.2 Absolute informational bounds on storage capacity 6.2.3 Coupling ...
Стр. xii
... Results for learning in learning modes 9.2 Learning in Modes 9.2.1 Perceptron learning 433 434 434 . 9.2.2 ANN learning by perceptron algorithm . 438 9.2.3 Local learning of the Kohonen synaptic matrix . 441 9.3 Natural Learning ...
... Results for learning in learning modes 9.2 Learning in Modes 9.2.1 Perceptron learning 433 434 434 . 9.2.2 ANN learning by perceptron algorithm . 438 9.2.3 Local learning of the Kohonen synaptic matrix . 441 9.3 Natural Learning ...
Стр. xiii
Извините, доступ к содержанию этой страницы ограничен..
Извините, доступ к содержанию этой страницы ограничен..
Стр. xiv
Извините, доступ к содержанию этой страницы ограничен..
Извините, доступ к содержанию этой страницы ограничен..
Содержание
II | 1 |
III | 3 |
IV | 5 |
V | 9 |
VI | 12 |
VII | 15 |
VIII | 17 |
IX | 18 |
XCV | 241 |
XCVII | 243 |
XCVIII | 245 |
XCIX | 248 |
C | 251 |
CI | 253 |
CII | 255 |
CIII | 256 |
X | 20 |
XI | 25 |
XII | 27 |
XIII | 31 |
XIV | 33 |
XV | 35 |
XVI | 38 |
XVII | 44 |
XIX | 45 |
XX | 48 |
53 | |
XXII | 58 |
XXIII | 63 |
XXIV | 65 |
XXV | 68 |
XXVI | 70 |
XXVII | 72 |
XXVIII | 74 |
XXIX | 79 |
XXX | 81 |
XXXI | 84 |
XXXII | 85 |
XXXIII | 87 |
XXXIV | 89 |
XXXV | 91 |
XXXVI | 95 |
XXXVII | 97 |
XXXVIII | 101 |
XXXIX | 105 |
XL | 108 |
XLI | 112 |
XLII | 119 |
XLIII | 125 |
XLIV | 126 |
XLV | 127 |
XLVI | 129 |
XLVII | 131 |
XLVIII | 133 |
XLIX | 141 |
LI | 142 |
LII | 143 |
LIII | 145 |
LIV | 146 |
LV | 147 |
LVI | 150 |
LVII | 152 |
LVIII | 153 |
LIX | 155 |
LX | 158 |
LXI | 162 |
LXII | 166 |
LXIII | 169 |
LXIV | 170 |
LXV | 172 |
LXVI | 174 |
LXVII | 178 |
LXVIII | 180 |
LXIX | 181 |
LXX | 187 |
LXXI | 189 |
LXXII | 190 |
LXXIII | 192 |
LXXIV | 194 |
LXXV | 198 |
LXXVI | 199 |
LXXVII | 200 |
LXXVIII | 201 |
LXXIX | 206 |
LXXX | 208 |
LXXXI | 209 |
LXXXII | 211 |
LXXXIII | 212 |
LXXXIV | 213 |
LXXXV | 215 |
LXXXVI | 216 |
LXXXVII | 218 |
LXXXVIII | 221 |
LXXXIX | 226 |
XC | 229 |
XCI | 231 |
XCII | 235 |
XCIII | 238 |
XCIV | 239 |
CIV | 259 |
CV | 262 |
CVII | 266 |
267 | |
CIX | 271 |
CX | 273 |
CXI | 275 |
CXIII | 278 |
CXIV | 283 |
CXV | 285 |
CXVI | 289 |
CXVII | 294 |
CXVIII | 299 |
CXIX | 304 |
CXX | 308 |
CXXI | 312 |
CXXII | 315 |
CXXIII | 318 |
CXXIV | 324 |
CXXV | 328 |
CXXVI | 330 |
CXXVII | 332 |
CXXVIII | 339 |
342 | |
CXXX | 345 |
CXXXI | 347 |
CXXXII | 352 |
CXXXIII | 355 |
CXXXIV | 357 |
CXXXV | 359 |
CXXXVI | 362 |
CXXXVII | 363 |
CXXXVIII | 366 |
CXXXIX | 368 |
CXL | 370 |
CXLI | 375 |
CXLIII | 377 |
CXLIV | 378 |
CXLV | 380 |
CXLVI | 384 |
CXLVII | 385 |
CXLVIII | 387 |
CXLIX | 388 |
CL | 389 |
CLI | 391 |
CLII | 396 |
CLIII | 398 |
CLIV | 403 |
CLV | 405 |
CLVI | 409 |
CLVII | 410 |
CLVIII | 412 |
CLX | 414 |
CLXI | 418 |
CLXII | 420 |
CLXIII | 422 |
CLXIV | 423 |
CLXV | 424 |
CLXVII | 425 |
426 | |
CLXIX | 428 |
CLXX | 430 |
CLXXI | 432 |
CLXXII | 433 |
CLXXIII | 434 |
CLXXIV | 438 |
CLXXV | 441 |
CLXXVI | 443 |
CLXXVII | 444 |
CLXXVIII | 447 |
CLXXIX | 450 |
CLXXX | 455 |
CLXXXI | 458 |
CLXXXIII | 461 |
CLXXXIV | 462 |
CLXXXV | 465 |
CLXXXVI | 469 |
CLXXXVII | 474 |
CLXXXVIII | 477 |
479 | |
CXC | 481 |
487 | |
Другие издания - Просмотреть все
Modeling Brain Function: The World of Attractor Neural Networks Daniel J. Amit Недоступно для просмотра - 1989 |
Часто встречающиеся слова и выражения
action potential activity ANN's asynchronous dynamics attractor average axon basins of attraction becomes behavior biological bits Chapter cognitive computation correlations corresponding cycle-time decreases described detailed balance dilution discussion distribution dynamical process eigen-value energy ergodicity excitatory fact ferromagnetic Figure finite fixed point free-energy fully connected function Hamming distance hence implies inhibitory initial input Ising model learning local field Lyapunov function magnetization mean-field equations memorized patterns memory minima modification neural networks neurons noise level noiseless non-ergodicity non-zero number of patterns output overlaps parameter perceptron phase potential pre-synaptic present probability PSP's random patterns random variables result retrieval quality right hand side Section simulations single solutions spike spin-glass spins spurious stable stimulus stochastic storage capacity stored patterns structure synapses synaptic efficacies synaptic matrix synchronous temperature temporal sequences term threshold tion trajectories transition uncorrelated updating values zero