Реклама. ООО «ЛитРес», ИНН: 7719571260.
From the authors
Part 1. A New Kind of Neural Network: Progress Artificial Neural Network (PANN)
1. Introduction to the Problem. Where did neural networks come from, and why are we unsatisfied with them?
2. Scientific and technical foundations of the PANN network. In this chapter, we will describe the main design features and the theoretical basics of the PANN network
3. New Opportunities for the Development of Artificial Intelligence Based on PANN and TRIZ
Part 2. PANN Practice
4. Matrix_PANN Software Description. Matrix_PANN (release 1) is a universal software for recognizing numerical images presented as pictures (graphic files)
5. Some experiments with Matrix_PANN. In most cases, PANN testing aims to compare it with classical neural networks. It would seem that it is not difficult to load a classic neural network and PANN into one computer and test them on the same tasks. However, it is more complicated due to the high heterogeneity of the objects of comparison. Like a child’s question: who is stronger, a tank or a submarine?
Part 3. Prospects for the use of PANN
6. Ongoing work to improve PANN. Progress, Inc., is constantly conducting research and development work in theoretical and practical directions. Some of these are at an early stage. Still, even today, it is possible to provide a general picture of the development of PANN technology and artificial intelligence based on it
7. Applications of PANN
Appendices
Appendix 1. Problems of Classical Neural Networks
Appendix 2. Icons and fields of the program Matrix_PANN
Appendix 3. Patents
Appendix 4. Useful links