Artificial Neural Systems: Principle and Practice

Research and Developments in Neural Networks

Author(s): Pierre Lorrentz

Pp: 217-235 (19)

DOI: 10.2174/9781681080901115010013

* (Excluding Mailing and Handling)

Abstract

Two categories of ANN systems are able to model any intelligent Expert in great detail. These are Bayesian network, and neuromorphic network. Both are hampered by lack of adequate resources and lack of human knowledge. Research and development on these two categories of ANN systems is the subject of this chapter. The first section of chapter 11, on Bayesian network, specifically describes Hybrid Monte Carlo (HMC) and associated algorithms, after which areas of possible researches are highlighted. The second section is on neuromorphic network. It presents the current state of industrial development. The chapter has taken care to omit those conceptual developments which may not be achievable in near future. Illustration of the recent neuromorphic design has been given in concluding the second section. The chapter has provided research and development information resources on two advanced ANN systems.


Keywords: Average error, CMOS, Comlex-conjugate Eigenvalue, Efficacy, Hamiltonian system, Harmonic oscillator, Hybrid Monte Carlo (HMC), Leapfrog algorithm, Long-Term Depression (LTD), Long-Term Potentiation (LTP), Markov-Chain Monte Carlo (MCMC), Multi-dimensional matrix, Omyleyan integrator, Pulse-Width Modulation ( PWM), Random-number generator, Shadow Hamiltonian, Simplectic, Spike-Timing-Dependent-Plasticity (STDP) computation, Titanium dioxide, Verlet velocity.

Related Journals
Related Books
© 2024 Bentham Science Publishers | Privacy Policy