Πέμπτη, 11 Δεκεμβρίου 2014

Deep Neural Networks are Easily Fooled!

In an article that was recently posted to the arXiv and is entitled Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images, the authors discuss how Deep neural networks (DNNs) can be fooled when performing visual classification. In particular, the show how  easy it is to produce images that are completely unrecognizable to humans yet that  DNNs believe they are recognizable objects with 99.99% confidence...!

Σάββατο, 20 Σεπτεμβρίου 2014

Δευτέρα, 25 Αυγούστου 2014

Constructive Hypercomputation

Constructivists assert that one has to construct a mathematical object in order  to show that it exists. And for some reasons they reject hypercomputation. In particular, Rasoul Ramezanian notes correctly in A Hypercomputation in Brouwer's Constructivism that for Brouwer, who was the founder of the mathematical philosophy of intuitionism, something exists as long there is a mental construction for it and this is exactly the reason for the rejection. Some constructivists do not accept that there are infinite objects at all. In fact, some assert that there are 21000 elementary particles in the Universe and so they believe this is the largest number! To me such ideas are absurd. But Ramezanian concludes that intuitionism can co-exist with hypercomputation. Moreover, he presents his Persistent Evolutionary Turing Machines, which is a couple N = (⟨z0, z1,…, zi⟩, f) where z0, z1,…, zi is a growing sequence of codes of deterministic Turing machines, and f (called the persistently evolutionary function) is a computable partial function from Σ× Σ to Σ. Ramezanian demands that f has certain properties and from there he goes on to explore the hypercomputational capabilities of this machine.

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.

Σάββατο, 12 Ιουλίου 2014

Hypercomputation and the Axiom of Choice

In the preface of my book on hypercomputation I have stated that all models of computation described in the book assume the axiom of choice.  Instead of explaining  explicitly why it is needed. I give an excerpt from Gregory H. Moore's prologue to  Zermelo's Axiom of Choice in the hope that readers will understand why it is needed.
 Yet  without the Axiom, mathematics today would be quite different. The very nature of modern mathematics would be altered and, if the Axiom's most severe constructivist critics prevailed, mathematics would be reduced to a collection of algorithms. Indeed, the Axiom epitomizes the fundamental changes—mathematical, philosophical, and psycological—that took place when mathematicians seriously began to study infinite collections of sets.

Πέμπτη, 20 Φεβρουαρίου 2014

Is computation observer-relative?

The 7th AISB Symposium on Computing and Philosophy will examine whether computation is observer-related. In different words, participants will discuss whether computation is a sponteneous natural phenomenon or not. I think that computation, like art, is not a natural phenomenon. Nature is not a sculpturer or a painter, and for that matter not a programmer. To animals, a sculpture is just a stone or a piece of metal and that's all. Flowers are not beautiful or ugly: they just attract bees and other insects. Mountains are not fearsome and lakes are not picturesque. Only humans give this attributes to these physical entities. Similarly, no chair and no desk computes anything. In fact, even a computer does not compute anything unless someone would be able to interpret the result of the computation. I am sure that if one could present a computer to Aristotle he could not easily realize what kind of machine it is.

Quantum computing and mass media

In a recent issue of Time magazine there was an article about quantum computing entitled The Quantum Quest for a Revolutionary Computer. The article describes D-Wave's machine and how quantum computing might affect our lives.

Superluminal Particles and Hypercomputation

Quite recently, Takaaki Musha published a book entitled Superluminal Particles and Hypercomputation. I have not read the book but from the description I see that he proposes a new model of computation that is based on the existence of tachyons, that is, particles that travel faster than the light. I suppose that in Possibility of Hypercomputation from the Standpoint ofSuperluminal Particles he presents an earlier version of his idea.

Σάββατο, 18 Ιανουαρίου 2014

The Mathematical Universe

Today I read critical blog-post on the Mathematical Universe, that is the idea that "physical reality is a mathematical structure". Of course, this idea is surprisingly similar to the idea that the universe is a computer. In a sense, one could argue that the two ideas are identical. What puzzles me the most is that both physics and computer science are following very dangerous paths…
 

A "Solution" to Riemann Hypothesis

Riemann hypothesi s is "is a conjecture that the Riemann zeta function has its zeros only at the negative even integers and complex n...