Special Issue "Statistical Mechanics of Neural Networks"
Deadline for manuscript submissions: closed (30 June 2019) | Viewed by 14881
Neural networks are highly interconnected systems of identical elements called neurons, which capture the basic physiological features of biological nerve cells. They serve as models to explore the collective behavior of nervous systems of living organisms. They are also applied in the study and design of artificial intelligence systems performing such functions as learning, information storage and retrieval, pattern recognition and decision making. The history of neural network modeling begins with the work of McCulloch and Pitts, who introduced in 1943 the notion of the formal neuron as a two-state threshold element and showed that a network of such elements can perform any logical calculation. A landmark in this history was the work of Hopfield, who suggested a fruitful analogy between the asymptotic dynamics of such networks and equilibrium properties of random magnetic systems. Hopfield’s work paved the road to the introduction of concepts and methods of statistical mechanics of random physical systems to the study of neural networks. Neural networks are oversimplified representations of the biological networks they are meant to emulate, but they can be systematically analyzed, numerically and sometimes even analytically. Thus, they can shed light on the principles of information processing in biological systems. The statistical analysis of neural networks became the cornerstone of the emerging discipline of computational neuroscience.
This is a call for papers on different aspects of the field of statistical mechanics of neural networks—from historical perspectives, to contemporary applications in brain research and artificial intelligence.
Prof. Dr. Hanoch Gutfreund
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
- Associative memory
- Hebbian learning rules
- Hopfield models
- Ising spin models
- Network dynamics
- Neural computation
- Synapses, inhibition and excitation
- Temporal patterns
- Information storage capacity
- Information retrieval
- Pattern recognition