An introduction to artificial neural networks

C. A. L. Bailer-Jones; R. Gupta; H. P. Singh

Home/Archive/arXiv

arXiv · astro-ph/0102224

An introduction to artificial neural networks

C. A. L. Bailer-Jones·R. Gupta·H. P. Singh

View original source ↗Read source document ↗Export metadata ↓

Abstract

Artificial neural networks are algorithms which have been developed to tackle a range of computational problems. These range from modelling brain function to making predictions of time-dependent phenomena to solving hard (NP-complete) problems. In this introduction we describe a single, yet very important, type of network known as a feedforward network. This network is a mathematical model which can be trained to learn an arbitrarily complex relationship between a data and a parameter domain, so can be used to solve interpolation and classification problems. We discuss the structure, training and interpretation of these networks, and their implementation, taking the classification of stellar spectra as an example.

Explore related subjects

astro-ph

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

C. A. L. Bailer-Jones, R. Gupta, H. P. Singh. 2001-02-13. An introduction to artificial neural networks. https://arxiv.org/abs/astro-ph/0102224

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2022

Dark Matter and Dark Energy

I briefly review our current understanding of dark matter and dark energy. The first part of this paper focusses on issues pertaining to dark matter including observational evidence for its existence, current constraints and the `abundance of substructure' and `cuspy core' issues which arise in CDM. I also briefly describe MOND. The second part of this review focusses on dark energy. In this part I discuss the significance of the cosmological constant problem which leads to a predicted value of the cosmological constant which is almost $10^{123}$ times larger than the observed value $\la/8πG \simeq 10^{-47}$GeV$^4$. Setting $\la$ to this small value ensures that the acceleration of the universe is a fairly recent phenomenon giving rise to the `cosmic coincidence' conundrum according to which we live during a special epoch when the density in matter and $\la$ are almost equal. Anthropic arguments are briefly discussed but more emphasis is placed upon dynamical dark energy models in which the equation of state is time dependent. These include Quintessence, Braneworld models, Chaplygin gas and Phantom energy. Model independent methods to determine the cosmic equation of state and the Statefinder diagnostic are also discussed. The Statefinder has the attractive property $\atridot/a H^3 = 1 $ for LCDM, which is helpful for differentiating between LCDM and rival dark energy models. The review ends with a brief discussion of the fate of the universe in dark energy models.

astro-ph↗

arXiv2022

MOND: A consequence of the geometric Leibniz Clock

Leibniz considered the notion of the 'empty physical space' to be a meaningless abstraction, and he held firmly to the view that the only significant thing was the set of relationships between 'objects', whatever these 'objects' might be. Similarly, he was equally clear in expressing his views about Newton's universal time, which he also considered to be a meaningless abstraction. In effect, for him, time was no more than a synonym for ordered change within a material system. The process of giving quantitative realization to this duality of non-Newtonian ideas forms the core of this work. A primary result arising is that every gravitating particle is no more than a clock - the geometric Leibniz Clock - which provides all the basic things: it conserves energy and angular momentum and satisfies the Weak Equivalence Principle. When the Clock is applied to model the concept of a galactic object within which all motions are circular, the characteristic properties of the MOND galaxy (asymptotic flatness, a critical acceleration scale, the baryonic Tully-Fisher relationship) are quantitatively reproduced in the resulting Leibniz galaxy. In short, the characteristic essence of MOND has its source in the geometric Leibniz Clock.

astro-ph↗

arXiv2020

Cosmic Variance and Its Effect on the Luminosity Function Determination in Deep High z Surveys

We study cosmic variance in deep high redshift surveys and its influence on the determination of the luminosity function for high redshift galaxies. For several survey geometries relevant for HST and JWST instruments, we characterize the distribution of the galaxy number counts. This is obtained by means of analytic estimates via the two point correlation function in extended Press-Schechter theory as well as by using synthetic catalogs extracted from N-body cosmological simulations of structure formation. We adopt a simple luminosity - dark halo mass relation to investigate the environment effects on the fitting of the luminosity function. We show that in addition to variations of the normalization of the luminosity function, a steepening of its slope is also expected in underdense fields, similarly to what is observed within voids in the local universe. Therefore, to avoid introducing artificial biases, caution must be taken when attempting to correct for field underdensity, such as in the case of HST UDF i-dropout sample, which exhibits a deficit of bright counts with respect to the average counts in GOODS. A public version of the cosmic variance calculator based on the two point correlation function integration is made available on the web.

astro-ph↗