On nil: The software constructor of neural networks
HT Siegelmann - Parallel Processing Letters, 1996 - World Scientific
Analog recurrent neural networks have attracted much attention lately as powerful tools of
automatic learning. However, they are not as popular in industry as should be justified by …
automatic learning. However, they are not as popular in industry as should be justified by …
[图书][B] Advances in neural information processing systems 19: Proceedings of the 2006 conference
B Schölkopf, J Platt, T Hofmann - 2007 - books.google.com
The annual Neural Information Processing Systems (NIPS) conference is the flagship
meeting on neural computation and machine learning. It draws a diverse group of attendees …
meeting on neural computation and machine learning. It draws a diverse group of attendees …
Challenges for a real-world information processing by means of real-time neural computation and real-conditions simulation
JC Herrero - International Work-Conference on Artificial Neural …, 1999 - Springer
Should we consider the dimensions of natural neural computation as they are known as a
result of the scientific research, we realize there is a long tomorrow before us, interested in …
result of the scientific research, we realize there is a long tomorrow before us, interested in …
A virtual machine for neural computers
JP Neto - Artificial Neural Networks–ICANN 2006: 16th …, 2006 - Springer
Neural Networks are mainly seen as algorithmic solutions for optimization and learning
tasks where the ability to spread the acquired knowledge into several neurons, ie, the use of …
tasks where the ability to spread the acquired knowledge into several neurons, ie, the use of …
[图书][B] Advances in Neural Information Processing Systems 9: Proceedings of the 1996 Conference
The annual conference on Neural Information Processing Systems (NIPS) is the flagship
conference on neural computation. It draws preeminent academic researchers from around …
conference on neural computation. It draws preeminent academic researchers from around …
Knowledge discovery based on neural networks
LM Fu - Communications of the ACM, 1999 - dl.acm.org
In symbolic AI, learning is often viewed as searching in a defined hypothesis space that
typically grows exponentially with the size of the problem to be solved. A practical learning …
typically grows exponentially with the size of the problem to be solved. A practical learning …
[PDF][PDF] Developments in computational intelligence and machine learning
This special issue of Neurocomputing comprises 17 original articles, which are extended
versions of selected papers from the 22nd European Symposium on Artificial Neural …
versions of selected papers from the 22nd European Symposium on Artificial Neural …
Neural expert systems
J Šíma - Neural networks, 1995 - Elsevier
The advantages and disadvantages of classical rule-based and neural approaches to expert
system design are complementary. We propose a strictly neural expert system architecture …
system design are complementary. We propose a strictly neural expert system architecture …
Neurules: improving the performance of symbolic rules
I Hatzilygeroudis, J Prentzas - International Journal on Artificial …, 2000 - World Scientific
In this paper, we present a method for improving the performance of classical symbolic rules.
This is achieved by introducing a type of hybrid rules, called neurules, which integrate …
This is achieved by introducing a type of hybrid rules, called neurules, which integrate …