Results 281 to 290 of about 124,788 (331)
Some of the next articles are maybe not open access.
Science, 1998
I would like to clarify some features of the program NeuroShell Easy described in “Neural nets for novices” by John Wass ( Science 's Compass, 7 Aug., p. 789). First, our Turboprop2 paradigm is not based on the General Regression Neural Network (GRNN), although GRNN is also in the package. Second, the software is not just for novices.
openaire +1 more source
I would like to clarify some features of the program NeuroShell Easy described in “Neural nets for novices” by John Wass ( Science 's Compass, 7 Aug., p. 789). First, our Turboprop2 paradigm is not based on the General Regression Neural Network (GRNN), although GRNN is also in the package. Second, the software is not just for novices.
openaire +1 more source
Adaptive-clustering optical neural net
Applied Optics, 1990Pattern recognition techniques (for clustering and linear discriminant function selection) are combined with neural net methods (that provide an automated method to combine linear discriminant functions into piecewise linear discriminant surfaces).
D P, Casasent, E, Barnard
openaire +2 more sources
Engineering Multiversion Neural-Net Systems
Neural Computation, 1996In this paper we address the problem of constructing reliable neural-net implementations, given the assumption that any particular implementation will not be totally correct. The approach taken in this paper is to organize the inevitable errors so as to minimize their impact in the context of a multiversion system, i.e., the system functionality is ...
D, Partridge, W B, Yates
openaire +2 more sources
2017
When problems are complex and cannot be solved through conventional methods such as statistical or management science models, and when human expertise is not sufficient for efficiently finding high-quality solutions, we can consider the use of machine learning techniques.
Brian R. Huguenard, Deborah J. Ballou
openaire +1 more source
When problems are complex and cannot be solved through conventional methods such as statistical or management science models, and when human expertise is not sufficient for efficiently finding high-quality solutions, we can consider the use of machine learning techniques.
Brian R. Huguenard, Deborah J. Ballou
openaire +1 more source
International Journal of Intelligent Systems, 1994
We suggest a description of thermodynamical systems, focusing on near-to-equilibrium states of the systems, within the structure of random graphs to map them to neural nets. We then use the component subgraph configurations of the random graphs that are the stationary states of the near-to-equilibrium systems to represent concepts in an unstructured ...
Nor, Khalid Md. +4 more
openaire +1 more source
We suggest a description of thermodynamical systems, focusing on near-to-equilibrium states of the systems, within the structure of random graphs to map them to neural nets. We then use the component subgraph configurations of the random graphs that are the stationary states of the near-to-equilibrium systems to represent concepts in an unstructured ...
Nor, Khalid Md. +4 more
openaire +1 more source
1998
The objective of this chapter is to show how to construct hybrid neural nets (HNN) to be computationally identical to discrete fuzzy expert systems (discussed in Chapter 4) and certain fuzzy controllers. An example of a 2 — 3 — 1 HNN is shown in Figure 5.1. Figure 5.1 is similar to Figure 3.1, however, the output y will be computed differently.
James J. Buckley, Thomas Feuring
openaire +1 more source
The objective of this chapter is to show how to construct hybrid neural nets (HNN) to be computationally identical to discrete fuzzy expert systems (discussed in Chapter 4) and certain fuzzy controllers. An example of a 2 — 3 — 1 HNN is shown in Figure 5.1. Figure 5.1 is similar to Figure 3.1, however, the output y will be computed differently.
James J. Buckley, Thomas Feuring
openaire +1 more source
Survival analysis and neural nets
Statistics in Medicine, 1994AbstractWe consider feed‐forward neural nets and their relation to regression models for survival data. We show how the back‐propagation algorithm may be used to obtain maximum likelihood estimates in certain standard regression models for survival data, as well as in various generalizations of these.
Liestøl, K. +2 more
openaire +2 more sources
Communications of the ACM, 2019
Yoshua Bengio, Geoffrey Hinton, and Yann LeCun this month will receive the 2018 ACM A.M. Turing Award for conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing.
openaire +1 more source
Yoshua Bengio, Geoffrey Hinton, and Yann LeCun this month will receive the 2018 ACM A.M. Turing Award for conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing.
openaire +1 more source
1998
This chapter, and the next three chapters, are a fuzzification of Chapters 3, 4 and 5. In this chapter we fuzzify neural nets (Chapter 3). In the next chapter we fuzzify the first approximation results (Chapter 4) into the second approximation results. Hybrid neural netsh (Chapter 5) are fuzzified into hybrid fuzzy neural nets in Chapters 9 and 10.
James J. Buckley, Thomas Feuring
openaire +1 more source
This chapter, and the next three chapters, are a fuzzification of Chapters 3, 4 and 5. In this chapter we fuzzify neural nets (Chapter 3). In the next chapter we fuzzify the first approximation results (Chapter 4) into the second approximation results. Hybrid neural netsh (Chapter 5) are fuzzified into hybrid fuzzy neural nets in Chapters 9 and 10.
James J. Buckley, Thomas Feuring
openaire +1 more source
2001
Conventional neural networks work by changing the synaptical weights between their neurons. New neural nets (NNN) are presented, using the recording of temporal sequences of activity, generated by various patterns in chains of neurons, to store and reproduce those patterns.
openaire +1 more source
Conventional neural networks work by changing the synaptical weights between their neurons. New neural nets (NNN) are presented, using the recording of temporal sequences of activity, generated by various patterns in chains of neurons, to store and reproduce those patterns.
openaire +1 more source