Artificial Intelligence

1902 Submissions

[29] viXra:1902.0485 [pdf] submitted on 2019-02-27 08:57:46

Spiking Artificial Intelligent Devices

Authors: George Rajna
Comments: 45 Pages.

The software program works best when patched in to programs meant to train new artificial-intelligence equipment, so Whetstone doesn't have to overcome learned patterns with already established energy minimums. [26] New work leveraging machine learning could increase the efficiency of optical telecommunications networks. [25] Physicists in the US have used machine learning to determine the phase diagram of a system of 12 idealized quantum particles to a higher precision than ever before. [24]
Category: Artificial Intelligence

[28] viXra:1902.0445 [pdf] submitted on 2019-02-25 05:47:46

Selfgan-not a Gan But Punch Itself

Authors: Hecong Wu
Comments: 5 Pages.

In my research, I modified the basic structure of GAN, let G and D train together, and use dynamic loss weights to achieve a relatively balanced training.
Category: Artificial Intelligence

[27] viXra:1902.0442 [pdf] submitted on 2019-02-25 07:18:29

Machine Learning Optical Networks

Authors: George Rajna
Comments: 43 Pages.

New work leveraging machine learning could increase the efficiency of optical telecommunications networks. [25] Physicists in the US have used machine learning to determine the phase diagram of a system of 12 idealized quantum particles to a higher precision than ever before. [24] The research group took advantage of a system at SLAC's Stanford Synchrotron Radiation Lightsource (SSRL) that combines machine learning—a form of artificial intelligence where computer algorithms glean knowledge from enormous amounts of data—with experiments that quickly make and screen hundreds of sample materials at a time. [23]
Category: Artificial Intelligence

[26] viXra:1902.0431 [pdf] submitted on 2019-02-25 23:11:53

Higher Order Sequence Of Primes {Version 2}

Authors: Ramesh Chandra Bagadi
Comments: 3 Pages.

In this research manuscript, the author has presented a novel notion of Higher Order Prime Numbers.
Category: Artificial Intelligence

[25] viXra:1902.0386 [pdf] submitted on 2019-02-22 06:21:37

Diversity of Ensembles for Data Stream Classification

Authors: Mohamed Souhayel Abassi
Comments: 9 Pages.

When constructing a classifier ensemble, diversity among the base classifiers is one of the important characteristics. Several studies have been made in the context of standard static data, in particular when analyzing the relationship between a high ensemble predictive performance and the diversity of its components. Besides, ensembles of learning machines have been performed to learn in the presence of concept drift and adapt to it. However,diversity measureshave not received much research interest for evolving data streams. Only a few researchers directly consider promoting diversity while constructing an ensemble or rebuilding them in the moment of detecting drifts. In this paper, we present a theoretical analysis of different diversity measures and relate them to the success of ensemble learning algorithms for streaming data. The analysis provides a deeper understanding of the concept of diversity and its impact on online ensemble Learning in the presence of concept drift. More precisely, we are interested in answering the following research question; Which commonly used diversity measures are used in the context of static-data ensembles and how far are they applicable in the context of streaming data ensembles?
Category: Artificial Intelligence

[24] viXra:1902.0376 [pdf] submitted on 2019-02-23 04:25:50

Neural Network Recognize Images

Authors: George Rajna
Comments: 48 Pages.

Physicists from Petrozavodsk State University have proposed a new method for oscillatory neural network to recognize simple images. Such networks with an adjustable synchronous state of individual neurons have, presumably, dynamics similar to neurons in the living brain. [27] Navid Borhani, a research-team member, says this machine learning approach is much simpler than other methods to reconstruct images passed through optical fibers, which require making a holographic measurement of the output. [26]
Category: Artificial Intelligence

[23] viXra:1902.0374 [pdf] submitted on 2019-02-23 04:49:25

Higher Order Sequence Of Primes

Authors: Ramesh Chandra Bagadi
Comments: 2 Pages.

In this research manuscript, the author has presented a novel notion of Higher Order Prime Numbers.
Category: Artificial Intelligence

[22] viXra:1902.0357 [pdf] submitted on 2019-02-22 00:17:05

Universal Forecasting Scheme For Any Time Series Sequence Using The Ananda-Damayanthi-Radha-Rohith Rishi Sequence Trends Of Any Set Of Positive Real Numbers {Version 2)

Authors: Ramesh Chandra Bagadi
Comments: 8 Pages.

In this research investigation, the author has detailed the Theory Of Universal Forecasting Scheme For Any Time Series Sequence Using The Ananda-Damayanthi-Radha-Rohith Rishi Sequence Trends Of Any Set Of Positive Real Numbers.
Category: Artificial Intelligence

[21] viXra:1902.0350 [pdf] submitted on 2019-02-20 06:43:54

Universal Forecasting Scheme For Any Time Series Sequence Using The Ananda-Damayanthi-Radha-Rohith Rishi Sequence Trends Of Any Set Of Positive Real Numbers

Authors: Ramesh Chandra Bagadi
Comments: 7 Pages.

In this research investigation, the author has detailed the Theory Of Universal Forecasting Scheme For Any Time Series Sequence Using The Ananda-Damayanthi-Radha-Rohith Rishi Sequence Trends Of Any Set Of Positive Real Numbers.
Category: Artificial Intelligence

[20] viXra:1902.0348 [pdf] submitted on 2019-02-20 07:31:03

Machine Learning Heavy Nuclei

Authors: George Rajna
Comments: 22 Pages.

A collaboration between the Facility for Rare Isotope Beams (FRIB) and the Department of Statistics and Probability (STT) at Michigan State University (MSU) estimated the boundaries of nuclear existence by applying statistical analysis to nuclear models, and assessed the impact of current and future FRIB experiments. [9] A trio of students from the University of Glasgow have developed a sophisticated artificial intelligence which could underpin the next phase of gravitational wave astronomy. [8]
Category: Artificial Intelligence

[19] viXra:1902.0322 [pdf] submitted on 2019-02-19 09:26:18

Cross Entropy of Belief Function

Authors: Fan Liu, Yangxue Li, Yong Deng
Comments: 12 Pages.

Dempster-Shafer evidence theory as an extension of Probability has wide applications in many fields. Recently, A new entropy called Deng entropy was proposed in evidence theory. There were a lot of discussions and applications about Deng entropy. However, there is no discussion on how to apply Deng entropy to measure the correlation between the two evidences. In this article, we first review and analyze some of the work related to mutual information. Then we propose the extension of Deng Entropy: joint Deng entropy, Conditional Deng entropy and cross Deng entropy. In addition, we prove the relevant properties of this entropy. Finally, we also proposed a method to obtain joint evidence.
Category: Artificial Intelligence

[18] viXra:1902.0288 [pdf] submitted on 2019-02-16 11:23:44

Genetic Programming

Authors: Domenico Oricchio
Comments: 1 Page.

I try to write a program that evolve in the time
Category: Artificial Intelligence

[17] viXra:1902.0279 [pdf] submitted on 2019-02-17 03:32:56

Divergence Measure of Belief Function

Authors: Yutong Song, Yong Deng
Comments: 3 Pages.

it is important to measure the divergent or conflicting degree among pieces of information for information preprocessing in case for the unreliable results which come from the combination of conflicting bodies of evidence using Dempster's combination rules. However, how to measure the divergence of different evidence is still an open issue. In this paper, a new divergence measure of belief function based on Deng entropy is proposed in order to measure the divergence of different belief function. The divergence measure is the generalization of Kullback-Leibler divergence for probability since when the basic probability assignment (BPA) is degenerated as probability, divergence measure is equal to Kullback-Leibler divergence. Numerical examples are used to illustrate the effectiveness of the proposed divergence measure.
Category: Artificial Intelligence

[16] viXra:1902.0254 [pdf] submitted on 2019-02-14 09:27:17

Machine Learning Plant's Secrets

Authors: George Rajna
Comments: 32 Pages.

Plants are master chemists, and Michigan State University researchers have unlocked their secret of producing specialized metabolites. [21] Marculescu, along with ECE Ph.D. student Chieh Lo, has developed a machine learning algorithm—called MPLasso—that uses data to infer associations and interactions between microbes in the GI microbiome. [20] A team of researchers from the University of Muenster in Germany has now demonstrated that this combination is extremely well suited to planning chemical syntheses—so-called retrosyntheses—with unprecedented efficiency. [19]
Category: Artificial Intelligence

[15] viXra:1902.0245 [pdf] replaced on 2019-12-10 14:27:32

Before We Can Find a Model, We Must Forget About Perfection

Authors: Dimiter Dobrev
Comments: 33 Pages.

With Reinforcement Learning we assume that a model of the world does exist. We assume furthermore that the model in question is perfect (i.e. it describes the world completely and unambiguously). This article will demonstrate that it does not make sense to search for the perfect model because this model is too complicated and practically impossible to find. We will show that we should abandon the pursuit of perfection and pursue Event-Driven (ED) models instead. These models are generalization of Markov Decision Process (MDP) models. This generalization is essential because nothing can be found without it. Rather than a single MDP, we will aim to find a raft of neat simple ED models each one describing a simple dependency or property. In other words, we will replace the search for a singular and complex perfect model with a search for a large number of simple models.
Category: Artificial Intelligence

[14] viXra:1902.0239 [pdf] submitted on 2019-02-13 23:19:21

The Ananda-Damayanthi-Radha-Rohith Rishi Sequence Trends Of Any Set Of Positive Real Numbers

Authors: Ramesh Chandra Bagadi
Comments: 5 Pages.

In this research investigation, the author has detailed the Theory Of Holistic Decomposition Of Any Set Of Prime Number, Natural Numbers, Positive Real Numbers As One Or More Sets Each With Some Periodicity Of The Number’s Non Integral Prime Basis Position Number.
Category: Artificial Intelligence

[13] viXra:1902.0236 [pdf] submitted on 2019-02-13 05:05:09

Theory Of Holistic Decomposition Of Any Set Of Any Natural Numbers As One Or More Sets Each With Some Periodicity Of The Number’s Non Integral Prime Basis Position Number. {Version 4}

Authors: Ramesh Chandra Bagadi
Comments: 5 Pages.

In this research investigation, the author has detailed the Theory Of Holistic Decomposition Of Any Set Of Any Natural Numbers As One Or More Sets Each With Some Periodicity Of The Number’s Non Integral Prime Basis Position Number.
Category: Artificial Intelligence

[12] viXra:1902.0220 [pdf] replaced on 2019-03-22 03:27:14

Comments on the Book "Architects of Intelligence" by Martin Ford in the Light of the SP Theory of Intelligence

Authors: J Gerard Wolff
Comments: 53 Pages.

The book "Architects of Intelligence" by Martin Ford presents conversations about AI between the author and influential researchers. Issues considered in the book are described in relation to features of the "SP System", meaning the "SP Theory of Intelligence" and its realisation in the "SP Computer Model", both outlined in an appendix. The SP System has the potential to solve most of the problems in AI described in the book, and some others. Strengths and potential of the SP System, which in many cases contrast with weaknesses of deep neural networks (DNNs), include the following: a top-down research strategy has yielded a system with a favourable combination of conceptual "Simplicity" with descriptive or explanatory "Power"; the SP System has strengths and potential with both symbolic and non-symbolic kinds of knowledge and processing; the system has strengths and long-term potential in pattern recognition; it is free of the tendency of DNNs to make large and unexpected errors in recognition; the system has strengths and potential in unsupervised learning, including grammatical inference; the SP Theory of Intelligence provides a theoretically coherent basis for generalisation and the avoidance of under- or over-generalisations; that theory of generalisation may help improve the safety of driverless; the SP system, unlike DNNs, can achieve learning from a single occurrence or experience; it has relatively tiny demands for computational resources and volumes of data, with potential for much higher speeds in learning; the system, unlike most DNNs, has strengths in transfer learning; unlike DNNs, it provides transparency in the representation of knowledge and an audit trail for all its processing; the system has strengths and potential in the processing of natural language; it exhibits several different kinds of probabilistic reasoning; the system has strengths and potential in commonsense reasoning and the representation of commonsense knowledge; other strengths include information compression, biological validity, scope for adaptation, and freedom from catastrophic forgetting. Despite the importance of motivations and emotions, no attempt has been made in the SP research to investigate these areas.
Category: Artificial Intelligence

[11] viXra:1902.0195 [pdf] submitted on 2019-02-11 08:39:31

Machine Learning Quantum Fireworks

Authors: George Rajna
Comments: 43 Pages.

A greater understanding of these behaviors could one day feed into technology, he said, such as ways to extend the reach of quantum networks across greater distances. [25] Physicists in the US have used machine learning to determine the phase diagram of a system of 12 idealized quantum particles to a higher precision than ever before. [24] The research group took advantage of a system at SLAC's Stanford Synchrotron Radiation Lightsource (SSRL) that combines machine learning—a form of artificial intelligence where computer algorithms glean knowledge from enormous amounts of data—with experiments that quickly make and screen hundreds of sample materials at a time. [23]
Category: Artificial Intelligence

[10] viXra:1902.0182 [pdf] submitted on 2019-02-11 02:15:05

Theory Of Holistic Decomposition Of Any Set Of Any Natural Numbers As One Or More Sets Each With Some Periodicity Of The Number’s Non Integral Prime Basis Position Number {Version 2}

Authors: Ramesh Chandra Bagadi
Comments: 4 Pages.

In this research investigation, the author has detailed the Theory Of Holistic Decomposition Of Any Set Of Any Natural Numbers As One Or More Sets Each With Some Periodicity Of The Number’s Non Integral Prime Basis Position Number.
Category: Artificial Intelligence

[9] viXra:1902.0174 [pdf] submitted on 2019-02-10 00:49:30

Theory Of Holistic Decomposition Of Any Set Of Any Natural Numbers As One Or More Sets Each With Some Periodicity Of The Number’s Non Integral Prime Basis Position Number

Authors: Ramesh Chandra Bagadi
Comments: 4 Pages.

In this research investigation, the author has detailed the Theory Of Holistic Decomposition Of Any Set Of Any Natural Numbers As One Or More Sets Each With Some Periodicity Of The Number’s Non Integral Prime Basis Position Number.
Category: Artificial Intelligence

[8] viXra:1902.0168 [pdf] submitted on 2019-02-09 05:50:49

Pictionary-Like Game in Robots

Authors: George Rajna
Comments: 54 Pages.

At the Allen Institute of Artificial Intelligence, a private research center perched on the north shore of Lake Union in Seattle, computer scientists are working on imbuing software with humanlike abilities to recognize images and understand language that could someday make that sort of collaboration possible. [30] A study by the Centre for Cognitive Science at TU Darmstadt shows that AI machines can indeed learn a moral compass from humans. [29] A group of researchers from MIT have already developed an AI robot that can assist in a labour room. [28]
Category: Artificial Intelligence

[7] viXra:1902.0151 [pdf] submitted on 2019-02-08 05:44:49

Theory Of Holistic Decomposition Of Any Set Of Given Primes As One Or More Sets Each With Some Periodicity Of The Prime Number’s Basis Position Number

Authors: Ramesh Chandra Bagadi
Comments: 3 Pages.

In this research investigation, the author has detailed the Theory Of Holistic Decomposition Of Any Set Of Given Primes As One Or More Sets Each With Some Periodicity Of The Prime Number’s Basis Position Number.
Category: Artificial Intelligence

[6] viXra:1902.0136 [pdf] submitted on 2019-02-08 03:10:15

Theory Of Decomposition Of Any Set Of Given Primes As One Or More Sets Each With Some Periodicity Of The Prime Number’s Basis Position Number

Authors: Ramesh Chandra Bagadi
Comments: 3 Pages.

In this research investigation, the author has detailed the Theory Of Decomposition Of Any Set Of Given Primes As One Or More Sets Each With Some Periodicity Of The Prime Number’s Basis Position Number.
Category: Artificial Intelligence

[5] viXra:1902.0123 [pdf] submitted on 2019-02-07 11:30:17

Moral Compass from Human Text

Authors: George Rajna
Comments: 52 Pages.

A study by the Centre for Cognitive Science at TU Darmstadt shows that AI machines can indeed learn a moral compass from humans. [29] A group of researchers from MIT have already developed an AI robot that can assist in a labour room. [28] Researchers at Fukuoka University, in Japan, have recently proposed a design methodology for configurable approximate arithmetic circuits. [27]
Category: Artificial Intelligence

[4] viXra:1902.0077 [pdf] submitted on 2019-02-05 02:28:35

Looking Into the Future of ai and the Embedded Systems Development with Interesting Intelligent Iot Applications Based on Specified Hardware & Software Via C/c++/ruby/ai/ml Related Concepts – a Short Technical Note

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication & Technical Notes

Looking into The Future of AI and the Embedded Systems Development With Interesting Intelligent IoT Applications based on Specified Hardware & Software via - C/C++/Ruby/AI/ML related Concepts – A Short Technical Note.
Category: Artificial Intelligence

[3] viXra:1902.0046 [pdf] submitted on 2019-02-03 08:35:44

1972 Proposal to Harvard for Backpropagation and Intelligent Reinforcement System

Authors: Paul Werbos
Comments: 32 Pages. What happened with this heresy from proposal to thesis is explained in Werbos (2006). Backwards differentiation in AD and neural nets: Past links and New Opportunities, In Automatic Differentiation, Springer

The great new revolution since 2010 in deep learning and machine learning based on neural networks is massively changing the world, and is a subject of great ruminations by high-level decision makers. (For example, see http://www.intelligence.senate.gov/hearings/open-hearing-worldwide-threats-hearing-1.) But the key design principles, such as backpropagation and reinforcement learning based on approximate dynamic programming (as in Alpha Go) were known, and were rejected as heresy, long ago. (See the recent book, https://www.amazon.com/Artificial-Intelligence-Neural-Networks-Computing-ebook/dp/B07K55YZRK, by the President of the International Neural Network Society, for an overview.) This paper, written in 1972 (and scanned into pdf in 2015), was the first explicit proposal for how to build a general reinforcement learning system, based on backpropagation and dynamic programming implemented through model neural networks, capable of converging to an optimal strategy of action in “any” environment informed by an understanding/model which it learns of how the environment works. Modern work uses more sophisticated language, but this effort to explain the underlying ideas in simpler language may still be of value to many. The 1974 thesis itself has been reprinted by Wiley, and has more than 4000 citations listed in scholar.google.com
Category: Artificial Intelligence

[2] viXra:1902.0033 [pdf] submitted on 2019-02-02 05:01:39

Software Detect Fake News

Authors: George Rajna
Comments: 48 Pages.

Fraunhofer researchers have developed a system that automatically analyzes social media posts, deliberately filtering out fake news and disinformation. [27] If you see a video of a politician speaking words he never would utter, or a Hollywood star improbably appearing in a cheap adult movie, don't adjust your television set—you may just be witnessing the future of "fake news." [26] Artificial intelligence can play chess, drive a car and diagnose medical issues. Examples include Google DeepMind's AlphaGo, Tesla's self-driving vehicles, and IBM's Watson. [25]
Category: Artificial Intelligence

[1] viXra:1902.0032 [pdf] submitted on 2019-02-02 05:18:09

Artificial Intelligence Harder for Hackers

Authors: George Rajna
Comments: 43 Pages.

Now, two Boston University computer scientists, working with researchers at Draper, a not-for-profit engineering solutions company located in Cambridge, have developed a tool that could make it harder for hackers to find their way into networks where they don't belong. [26] IBM, home of the question-answering computer system Watson, was by far the company with the largest portfolio of AI patent applications, with a total of 8,290 inventions, followed by Microsoft with 5,930, the report showed. [25] Researchers at Aalto University and the Technical University of Denmark have developed an artificial intelligence (AI) to seriously accelerate the development of new technologies from wearable electronics to flexible solar panels. [24]
Category: Artificial Intelligence