302:. The neural network is constructed by connecting adaptive filter components in a pipe filter flow. This allows for greater flexibility as custom networks can be built as well as custom components used by the network. In many cases this allows a combination of adaptive and non-adaptive components to work together. The data flow is controlled by a control system which is exchangeable as well as the adaptation algorithms. The other important feature is deployment capabilities.
25:
285:
178:
232:
environments, data analysis simulators use a relatively simple static neural network that can be configured. A majority of the data analysis simulators on the market use backpropagating networks or self-organizing maps as their core. The advantage of this type of software is that it is relatively easy to use.
188:
Historically, the most common type of neural network software was intended for researching neural network structures and algorithms. The primary purpose of this type of software is, through simulation, to gain a better understanding of the behavior and the properties of neural networks. Today in the
410:
PMML provides applications a vendor-independent method of defining models so that proprietary issues and incompatibilities are no longer a barrier to the exchange of models between applications. It allows users to develop models within one vendor's application, and use other vendors' applications to
164:
Neural network simulators are software applications that are used to simulate the behavior of artificial or biological neural networks. They focus on one or a limited number of specific types of neural networks. They are typically stand-alone and not intended to produce general neural networks that
256:
In 1997, the tLearn software was released to accompany a book. This was a return to the idea of providing a small, user-friendly, simulator that was designed with the novice in mind. tLearn allowed basic feed forward networks, along with simple recurrent networks, both of which can be trained by
231:
Unlike the research simulators, data analysis simulators are intended for practical applications of artificial neural networks. Their primary focus is on data mining and forecasting. Data analysis simulators usually have some form of preprocessing capabilities. Unlike the more general development
248:
volumes were released in 1986-87, they provided some relatively simple software. The original PDP software did not require any programming skills, which led to its adoption by a wide variety of researchers in diverse fields. The original PDP software was developed into a more powerful package
203:
In the study of biological neural networks however, simulation software is still the only available approach. In such simulators the physical biological and chemical properties of neural tissue, as well as the electromagnetic impulses between the neurons are studied.
370:
The majority implementations of neural networks available are however custom implementations in various programming languages and on various platforms. Basic types of neural networks are simple to implement directly. There are also many
313:, component based development environments are capable of deploying the developed neural network to these frameworks as inheritable components. In addition some software can also deploy these components to several platforms, such as
407:(PMML) has been proposed to address this need. PMML is an XML-based language which provides a way for applications to define and share neural network models (and other data mining models) between PMML compliant applications.
504:
McClelland, J.L., D.E. Rumelhart and the PDP Research Group (1986). Parallel
Distributed Processing: Explorations in the Microstructure of Cognition. Volume 2: Psychological and Biological Models, Cambridge, MA: MIT
260:
In 2011, the Basic Prop simulator was released. Basic Prop is a self-contained application, distributed as a platform neutral JAR file, that provides much of the same simple functionality as tLearn.
495:
Rumelhart, D.E., J.L. McClelland and the PDP Research Group (1986). Parallel
Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1: Foundations, Cambridge, MA: MIT Press
268:
Development environments for neural networks differ from the software described above primarily on two accounts – they can be used to develop custom types of neural networks and they support
411:
visualize, analyze, evaluate or otherwise use the models. Previously, this was very difficult, but with PMML, the exchange of models between compliant applications is now straightforward.
362:
A disadvantage of component-based development environments is that they are more complex than simulators. They require more learning to fully operate and are more complicated to develop.
557:
189:
study of artificial neural networks, simulators have largely been replaced by more general component based development environments as research platforms.
42:
456:
299:
419:
A range of products are being offered to produce and consume PMML. This ever-growing list includes the following neural network products:
466:
193:
89:
108:
61:
552:
404:
523:
Plunkett, K. and Elman, J.L., Exercises in
Rethinking Innateness: A Handbook for Connectionist Simulations (The MIT Press, 1997)
298:
A more modern type of development environments that are currently favored in both industrial and scientific use are based on a
68:
46:
384:
75:
536:
392:
310:
57:
35:
427:
141:
137:
403:
In order for neural network models to be shared by different applications, a common language is necessary. The
253:. With each development, the software has become more powerful, but also more daunting for use by beginners.
169:
to monitor the training process. Some simulators also visualize the physical structure of the neural network.
451:
149:
166:
372:
436:
STATISTICA: produces PMML for neural networks, data mining models and traditional statistical models.
343:
133:
82:
514:
McClelland and
Rumelhart "Explorations in Parallel Distributed Processing Handbook", MIT Press, 1987
471:
335:
250:
197:
375:
that contain neural network functionality and that can be used in custom implementations (such as
273:
212:
380:
324:
291:
269:
208:
220:
153:
314:
233:
216:
145:
423:
R: produces PMML for neural nets and other machine learning models via the package pmml.
446:
331:
328:
306:
546:
245:
165:
can be integrated in other software. Simulators usually have some form of built-in
461:
272:
of the neural network outside the environment. In some cases they have advanced
24:
430:, linear and logistic regression, decision trees, and other data mining models.
257:
the simple back propagation algorithm. tLearn has not been updated since 1999.
376:
339:
249:
called PDP++, which in turn has become an even more powerful platform called
125:
476:
433:
SPSS: produces PMML for neural networks as well as many other mining models.
321:
288:
284:
426:
SAS Enterprise Miner: produces PMML for several mining models, including
129:
177:
351:
388:
347:
283:
176:
181:
192:
Commonly used artificial neural network simulators include the
18:
383:, etc., typically providing bindings to languages such as
305:
With the advent of component-based frameworks such as
207:
Commonly used biological network simulators include
49:. Unsourced material may be challenged and removed.
320:Component based development environments include:
240:Simulators for teaching neural network theory
236:is one example of a data analysis simulator.
8:
276:, analysis and visualization capabilities.
109:Learn how and when to remove this message
294:component based development environment.
558:Applications of artificial intelligence
537:Comparison of Neural Network Simulators
488:
144:, and in some cases, a wider array of
346:component based environments include
7:
457:Comparison of deep learning software
47:adding citations to reliable sources
467:Integrated development environment
194:Stuttgart Neural Network Simulator
14:
184:research neural network simulator
140:, software concepts adapted from
405:Predictive Model Markup Language
23:
246:Parallel Distributed Processing
34:needs additional citations for
1:
415:PMML consumers and producers
342:integrated software. Free
574:
338:Neuro Laboratory, and the
142:biological neural networks
138:artificial neural networks
539:at University of Colorado
58:"Neural network software"
300:component based paradigm
264:Development environments
227:Data analysis simulators
553:Neural network software
452:Physical neural network
150:artificial intelligence
122:Neural network software
366:Custom neural networks
295:
185:
373:programming libraries
287:
180:
43:improve this article
472:Logistic regression
336:Scientific Software
173:Research simulators
296:
186:
119:
118:
111:
93:
565:
524:
521:
515:
512:
506:
502:
496:
493:
315:embedded systems
154:machine learning
146:adaptive systems
114:
107:
103:
100:
94:
92:
51:
27:
19:
16:Type of software
573:
572:
568:
567:
566:
564:
563:
562:
543:
542:
533:
528:
527:
522:
518:
513:
509:
503:
499:
494:
490:
485:
443:
428:neural networks
417:
401:
368:
360:
282:
280:Component based
266:
242:
234:Neural Designer
229:
175:
162:
115:
104:
98:
95:
52:
50:
40:
28:
17:
12:
11:
5:
571:
569:
561:
560:
555:
545:
544:
541:
540:
532:
531:External links
529:
526:
525:
516:
507:
497:
487:
486:
484:
481:
480:
479:
474:
469:
464:
459:
454:
449:
447:AI accelerator
442:
439:
438:
437:
434:
431:
424:
416:
413:
400:
397:
367:
364:
359:
356:
332:NeuroSolutions
329:NeuroDimension
281:
278:
265:
262:
241:
238:
228:
225:
174:
171:
161:
158:
117:
116:
99:September 2014
31:
29:
22:
15:
13:
10:
9:
6:
4:
3:
2:
570:
559:
556:
554:
551:
550:
548:
538:
535:
534:
530:
520:
517:
511:
508:
501:
498:
492:
489:
482:
478:
475:
473:
470:
468:
465:
463:
460:
458:
455:
453:
450:
448:
445:
444:
440:
435:
432:
429:
425:
422:
421:
420:
414:
412:
408:
406:
398:
396:
394:
390:
386:
382:
378:
374:
365:
363:
357:
355:
353:
349:
345:
341:
337:
333:
330:
326:
323:
318:
316:
312:
308:
303:
301:
293:
290:
286:
279:
277:
275:
274:preprocessing
271:
263:
261:
258:
254:
252:
247:
239:
237:
235:
226:
224:
222:
218:
214:
210:
205:
201:
199:
195:
190:
183:
179:
172:
170:
168:
167:visualization
159:
157:
155:
151:
147:
143:
139:
135:
131:
127:
123:
113:
110:
102:
91:
88:
84:
81:
77:
74:
70:
67:
63:
60: –
59:
55:
54:Find sources:
48:
44:
38:
37:
32:This article
30:
26:
21:
20:
519:
510:
500:
491:
418:
409:
402:
369:
361:
319:
304:
297:
267:
259:
255:
243:
230:
206:
202:
196:(SNNS), and
191:
187:
163:
136:, and apply
121:
120:
105:
96:
86:
79:
72:
65:
53:
41:Please help
36:verification
33:
462:Data Mining
344:open source
124:is used to
547:Categories
483:References
377:TensorFlow
340:LIONsolver
270:deployment
160:Simulators
69:newspapers
477:Memristor
399:Standards
358:Criticism
322:Peltarion
289:Peltarion
244:When the
441:See also
251:Emergent
198:Emergent
148:such as
130:research
126:simulate
352:Neuroph
325:Synapse
292:Synapse
213:GENESIS
134:develop
83:scholar
385:Python
381:Theano
209:Neuron
85:
78:
71:
64:
56:
505:Press
348:Encog
221:Brian
90:JSTOR
76:books
393:Java
350:and
311:Java
309:and
307:.NET
219:and
217:NEST
182:SNNS
152:and
62:news
395:).
389:C++
45:by
549::
391:,
387:,
379:,
354:.
334:,
327:,
317:.
223:.
215:,
211:,
200:.
156:.
132:,
128:,
112:)
106:(
101:)
97:(
87:·
80:·
73:·
66:·
39:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
