Affiliation:
1. Politecnico Di Milano University, Italy
Abstract
To achieve reliable system intelligence outstanding results, current computational system modeling and simulation community has to face and to solve two orders of modeling limitations at least. As a solution, the author proposes an exponential, pre-spatial arithmetic scheme (“all-powerful scheme”) by computational information conservation theory (CICT) to overcome the Information Double-Bind (IDB) problem and to thrive on both deterministic noise (DN) and random noise (RN) to develop powerful cognitive computational framework for deep learning, towards deep thinking applications. In a previous paper the author showed and discussed how this new CICT framework can help us to develop even competitive advanced quantum cognitive computational systems. An operative example is presented. This paper is a relevant contribution towards an effective and convenient “Science 2.0” universal computational framework to develop deeper learning and deep thinking system and application at your fingertips and beyond.
Reference56 articles.
1. Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. Proceedings ICLR ‘15. Retrieved from http://arxiv.org/abs/1409.0473
2. Quantum noise and information.;H.Bremermann;Proceedings of The 5th Berkeley Symposium on Mathematical Statistics and Probability,1965
3. Chen, Y., Luo, T., Liu, S., Zhang, S., He, L., Wang, J., . . .. (2014). Dadiannao: A machine-learning supercomputer. Proceedings 47th Annual IEEE/ACM International Symposium on MicroarchitectureMICRO ‘14 (pp. 609–622). .
4. Multi-column deep neural network for traffic sign classification
5. Ciresan, D., Meier, U., & Schmidhuber, J. (2012). Multi-column deep neural networks for image classification (Technical report). Retrieved from http://arxiv.org/abs/1202.2745