Implementing an Analog Recurrent Neural Network

-
A. Steven Younger, Emmett Redd, and Hava Siegelmann published a paper entitled  Development of Physical Super-Turing Analog Hardware, where they report their efforts to build a real hypercomputer. In particular, they present their work on the realization of Analog Recurrent Neural Networks (ARNN, for short). The theory of ARNNs is presented in Neural Networks and Analog Computation.In a nutshel, the ARNNs are generally more powerful than Turing machines and so they are classified as hypecomputers. Younger  et al. have designed and developed an OpticARNN which is depicted in the figure that follows:
Also, they have developed an electronic ARNN whose functional schematic follows:
These system have not been tested thoroughly and so one cannot draw definitive conclusions. The authors plan to build larger devices and continue their studies.

Σχόλια

Δημοσίευση σχολίου

Δημοφιλείς αναρτήσεις από αυτό το ιστολόγιο

A comment on a comment

-
Recently, "someone" posted a review of my book on hypercomputation on the Brains site. The reviewer argues that This area is full of problems, some of which are physico/mathematical and some of which are conceptual. Unfortunately, from a quick sample, Syropolous's book does not avoid common mistakes and confusions—some of which I've been trying to correct in my own work. First of all, I have to admit that back in 2004 I read a paper by this reviewer, but at that time I did not considered it interesting. However, after I read this review of my book, I read The Physical Church-Turing Thesis: Modest or Bold? , the reviewer's latest manuscript, in order to see what he meant by common mistakes and confusions and how he was trying to solve them. In this manuscript, the reviewer puts forth a number of criteria that every machine has to satisfy in order to be ``useful for physical computing.'' These criteria are: Readable Inputs and Outputs Process-Independ...
Διαβάστε περισσότερα

Is the Universe a Quantum Computer?

-
 The idea that the Universe (whatever we may mean by this) is a some sort of a computer is a recurring theme. Recently, Nature published an article by David L. Chandler that is entitled Could the Universe be a giant quantum computer? This article is actually a tribute to Edward Fredkin, who passed away last June. The main contribution of Fredkin to the philosophy of science is his "digital philosophy" that advocates the idea that the universe is a computer and everything in our universe is discrete. I would not like to argue against the validity of these ideas (I have done so in Hypercomputation: Computing Beyond the Church-Turing Barrier and in Demystifying Computation: A Hands-On Introduction ) . However, I would like to point out that if the Universe is not a computing device, in general, then it cannot be a quantum computer, in particular. Also, what I did not like with Chandler's article is that it takes it for granted that the Universe is a computer. He did not e...
Διαβάστε περισσότερα