Artificial Intelligence

1906 Submissions

[18] viXra:1906.0578 [pdf] submitted on 2019-06-30 11:15:42

Ai Tool in Rna Video Game

Authors: George Rajna
Comments: 52 Pages.

A new artificial-intelligence tool captures strategies used by top players of an internet-based videogame to design new RNA molecules. [31] A team of EPFL scientists has now written a machine-learning program that can predict, in record time, how atoms will respond to an applied magnetic field. [30] Researchers from the University of Luxembourg, Technische Universität Berlin, and the Fritz Haber Institute of the Max Planck Society have combined machine learning and quantum mechanics to predict the dynamics and atomic interactions in molecules. [29] For the first time, physicists have demonstrated that machine learning can reconstruct a quantum system based on relatively few experimental measurements. [28] AlphaZero plays very unusually; not like a human, but also not like a typical computer. Instead, it plays with "real artificial" intelligence. [27] Predictions for an AI-dominated future are increasingly common, but Antoine Blondeau has experience in reading, and arguably manipulating, the runes-he helped develop technology that evolved into predictive texting and Apple's Siri. [26] Artificial intelligence can improve health care by analyzing data from apps, smartphones and wearable technology. [25] Now, researchers at Google's DeepMind have developed a simple algorithm to handle such reasoning-and it has already beaten humans at a complex image comprehension test. [24] A marimba-playing robot with four arms and eight sticks is writing and playing its own compositions in a lab at the Georgia Institute of Technology. The pieces are generated using artificial intelligence and deep learning. [23] Now, a team of researchers at MIT and elsewhere has developed a new approach to such computations, using light instead of electricity, which they say could vastly improve the speed and efficiency of certain deep learning computations. [22] Physicists have found that the structure of certain types of quantum learning algorithms is very similar to their classical counterparts-a finding that will help scientists further develop the quantum versions. [21] We should remain optimistic that quantum computing and AI will continue to improve our lives, but we also should continue to hold companies, organizations, and governments accountable for how our private data is used, as well as the technology's impact on the environment. [20]
Category: Artificial Intelligence

[17] viXra:1906.0566 [pdf] submitted on 2019-06-29 06:30:52

Solving the Shortest Path Problem By Genetic and Ant Colony Optimization Algorithms

Authors: Eyman Yosef; A.A. Salama; M. Elsayed Wahed
Comments: 17 Pages.

In this paper I will present two different genetic and ant colony algorithms for solving a classic computer science problem: shortest path problems. I will first give a brief discussion on the general topics of the shortest path problem, genetic and ant colony algorithms.I will conclude by making some observations on the advantages and disadvantages of using genetic and ant colony algorithms to solve the shortest path problem and my opinion on the usefulness of the solutions and the future of this area of computer science
Category: Artificial Intelligence

[16] viXra:1906.0527 [pdf] submitted on 2019-06-28 00:40:54

[ Itensor + a Quantum Device + Dlibc++machine Learning Library ] to Probe [ Hardware-Software-Firmware ] Interaction with [ Critical Infrastructure + Smart Device + Iot + HPC ] in the Context of Advanced Medical Imaging a Novel Suggestion in Designing I

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication & Simple Suggestion

[ ITensor + a Quantum Device + dlibC++Machine Learning Library ] to Probe [ Hardware-Software-Firmware ] Interaction with [ Critical Infrastructure + Smart Device + IoT + HPC ] in the Context of Advanced Medical Imaging - A Novel Suggestion in Designing Intelligent Wireless Medical Imaging Platform Using Related Machine Learning Informatics.
Category: Artificial Intelligence

[15] viXra:1906.0433 [pdf] submitted on 2019-06-24 05:00:48

Evidential Distance Measure in Complex Belief Function Theory

Authors: Fuyuan Xiao
Comments: 2 Pages.

In this paper, an evidential distance measure is proposed which can measure the difference or dissimilarity between complex basic belief assignments (CBBAs), in which the CBBAs are composed of complex numbers. When the CBBAs are degenerated from complex numbers to real numbers, the proposed distance will degrade into the Jousselme et al.’s distance. Therefore, the proposed distance provides a promising way to measure the differences between evidences in a more general framework of complex plane space.
Category: Artificial Intelligence

[14] viXra:1906.0414 [pdf] submitted on 2019-06-20 07:14:47

Machine Learning Quantum Physics

Authors: George Rajna
Comments: 44 Pages.

A Cornell-led team has developed a way to use machine learning to analyze the data generated by scanning tunneling microscopy (STM)-a technique that produces subatomic scale images of electronic motions in material surfaces at varying energies, providing information unattainable by any other method. [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] Researchers at the UCLA Samueli School of Engineering have demonstrated that deep learning, a powerful form of artificial intelligence, can discern and enhance microscopic details in photos taken by smartphones. [22] Such are the big questions behind one of the new projects underway at the MIT-IBM Watson AI Laboratory, a collaboration for research on the frontiers of artificial intelligence. [21]
Category: Artificial Intelligence

[13] viXra:1906.0402 [pdf] submitted on 2019-06-21 01:17:46

Machine Learning Features for Malicious URL Filtering- The Survey

Authors: Smaranya Dey, Eshan Jain, Arunita Das
Comments: 8 Pages.

Malicious URL is the URL created for harmful purposes which contains spam, phishing, misleading applications like fake antiviruses or fake codecs. The use of this kind of URLs might lead to monetary loss, theft of sensitive information such as personal details or corporate data, disruption of operations, unauthorized access to system resources etc. Often these websites are built to look like a genuine website to deceive the users in installing malicious content in their systems. As per NetCraft January 2018 web server survey, there are 1.8 billion sites across 213 million unique domain names. According to Symantec Internet Security Threat Report 2018, 1 in 13 web requests lead to malware which is up 3% from 2016. Sudden rise of cyber-attacks in recent years makes this problem indispensable for both private and public organizations. The primary objective of the paper is to provide a near exhaustive set of meaningful features that can help professionals and practitioners to facilitate their own research and practical applications on malicious URL filtering. These features are systematically classified and described in keyword-based features, lexical features, content-based features (HTML and JavaScript), IP Address Properties based features, web-rank and score-based features. This paper also briefly discusses on how URL filtering techniques have evolved in the past. The paper talks about traditional techniques like blacklisting URLs, heuristic approaches while also highlighting the shortcomings of these approaches. We then touch upon newer machine learning based techniques like cosine similarity-based URL classification, Support Vector Machines and Neural Network based models.
Category: Artificial Intelligence

[12] viXra:1906.0399 [pdf] submitted on 2019-06-21 03:11:06

[ Halide/llvm/clang/dlibc++ Machine Learning Library Toolkit ] as hi-End Cryo-em Image Processing Software & Informatics Platform a Simple Short Communication on Using [ Halide/dlibc++ Machine Learning Library Toolkit/iot/hpc ]

Authors: Nirmal Tej Kumar
Comments: 7 Pages. Short Communication & Simple Suggestion

[ Halide/LLVM/Clang/dlibC++ Machine Learning Library Toolkit ] as HI-END cryo-EM Image Processing Software & Informatics Platform - A Simple Short Communication on Using [ Halide/dlibC++ Machine Learning Library Toolkit/IoT/HPC ] in a Related Heterogeneous Computing Environment R&D.
Category: Artificial Intelligence

[11] viXra:1906.0385 [pdf] submitted on 2019-06-21 11:01:50

AI Converts CT Images

Authors: George Rajna
Comments: 53 Pages.

An artificial intelligence (AI) algorithm can transform low-dose CT (LDCT) scans into high-quality exams that radiologists may even prefer over LDCT studies produced via commercial iterative reconstruction techniques. [31] A team of EPFL scientists has now written a machine-learning program that can predict, in record time, how atoms will respond to an applied magnetic field. [30] Researchers from the University of Luxembourg, Technische Universität Berlin, and the Fritz Haber Institute of the Max Planck Society have combined machine learning and quantum mechanics to predict the dynamics and atomic interactions in molecules. [29] For the first time, physicists have demonstrated that machine learning can reconstruct a quantum system based on relatively few experimental measurements. [28] AlphaZero plays very unusually; not like a human, but also not like a typical computer. Instead, it plays with "real artificial" intelligence. [27] Predictions for an AI-dominated future are increasingly common, but Antoine Blondeau has experience in reading, and arguably manipulating, the runes-he helped develop technology that evolved into predictive texting and Apple's Siri. [26] Artificial intelligence can improve health care by analyzing data from apps, smartphones and wearable technology. [25] Now, researchers at Google's DeepMind have developed a simple algorithm to handle such reasoning-and it has already beaten humans at a complex image comprehension test. [24] A marimba-playing robot with four arms and eight sticks is writing and playing its own compositions in a lab at the Georgia Institute of Technology. The pieces are generated using artificial intelligence and deep learning. [23] Now, a team of researchers at MIT and elsewhere has developed a new approach to such computations, using light instead of electricity, which they say could vastly improve the speed and efficiency of certain deep learning computations. [22] Physicists have found that the structure of certain types of quantum learning algorithms is very similar to their classical counterparts-a finding that will help scientists further develop the quantum versions. [21]
Category: Artificial Intelligence

[10] viXra:1906.0383 [pdf] submitted on 2019-06-21 13:51:15

Supervised Dimensionality Reduction for Multi-Label Nearest Neighbors

Authors: Reda ALAMI
Comments: 75 Pages.

The ML-kNN algorithm is one of the most famous and most efficient multi-label classifier. Its performances are very remarkable when compared with the other state-of-art multi-label classifiers. Nevertheless, it suffers from two major drawbacks: its accuracy crucially depends on the metric function used to compute distances between instances, and when dealing with high dimensions data, the neighborhoods identification task becomes very slow. So, both metric learning and dimensionality reduction are essential to improve the ML-kNN performances. In this report, we propose a novel multi-label Mahalanobis distance learned via a supervised dimensionality reduction approach that we call ML-ARP. ML-ARP is a process that adapts random projections on a multi-label dataset to improve the ML-kNN performances. Unlike most state of art multi-label dimensionality reduction approaches that solve eigenvalue or inverse problem, our method is iterative and scales up with high dimensions. There is no eigenvalue or inverse problems to solve. Experiments show that the ML-ARP allows us to highly upgrade the ML-kNN classifier. Statistical tests assert that the MLARP is better than the remaining state-of-art multi-label dimensionality reduction approaches
Category: Artificial Intelligence

[9] viXra:1906.0258 [pdf] submitted on 2019-06-14 22:47:13

Graph Signal Processing: Towards the Diffused Spectral Clustering

Authors: Reda ALAMI
Comments: 5 Pages.

Graph signal processing is an emerging field of research. When the structure of signalscanberepresentedasagraph,itallowstofullyexploittheirinherentstructure. It has been shown that the normalized graph Laplacian matrix plays a major role in the characterization of a signal on a graph. Moreover, this matrix plays a major role in clustering large data set. In this paper, we present the diffused spectral clustering: a novel handwritten digits clustering algorithm based on the normalizedgraphLaplacianproperties. It’saclevercombinationbetweenagraph feature space transformation and the spectral clustering algorithm. Experimentally, our proposal outperforms the other algorithms of the state-of-art.
Category: Artificial Intelligence

[8] viXra:1906.0211 [pdf] submitted on 2019-06-12 14:18:43

Sparse Ensemble Learning with Truncated Convolutional Autoencoders for Cleaning Stained Documents

Authors: Anant Khandelwal
Comments: 14 Pages.

This paper mainly focus on how to extract clean text from the stained document. It may happen sometimes that due to stains it becomes very difficult to understand the documents and from the previous work it has been seen that one particular modelling technique either through Image processing or Machine learning which alone can’t perform for all the cases in general. As we all know ensemble techniques combine many of the modelling techniques and result in much reduced error that would not be possible by just having single model. But the features used for different models should be sparse or non-overlapping enough to guarantee the independence of each of the modelling techniques. XGBoost is one such ensemble technique in comparison to gradient boosting machines which are very slow due to this it’s not possible to combine more than three models with reasonable execution time. This work mainly focus on combining the truncated convolutional Autoencoders with sparsity take into account to that of machine learning and Image processing models using XGBoost such that the whole model results in much reduced error as compared to single modelling techniques. Experimentation’s are carried out on the public dataset NoisyOffice published on UCI machine learning repository, this dataset contains training, validation and test dataset with variety of noisy greyscale images some with ink spots, coffee spots and creased documents. Evaluation metric is taken to be RMSE(Reduced Mean Squared Error) to show the performance improvement on the variety of images which are corrupted badly
Category: Artificial Intelligence

[7] viXra:1906.0198 [pdf] submitted on 2019-06-11 06:10:22

Home work

Authors: Tuan Yugyi
Comments: 7 Pages.

Title, authors and abstract should also be included in the PdF file. These should be in English. If the submission is not in English please translate the title and abstract here. You can include basic HTML is the abstract for formatting if necessary. (e.g. subscripts, italics, line breaks and special characters) Please do not use links, images, bold, font changes or character sizes or colours.Title, authors and abstract should also be included in the PdF file. These should be in English. If the submission is not in English please translate the title and abstract here. You can include basic HTML is the abstract for formatting if necessary. (e.g. subscripts, italics, line breaks and special characters) Please do not use links, images, bold, font changes or character sizes or colours.Title, authors and abstract should also be included in the PdF file. These should be in English. If the submission is not in English please translate the title and abstract here. You can include basic HTML is the abstract for formatting if necessary. (e.g. subscripts, italics, line breaks and special characters) Please do not use links, images, bold, font changes or character sizes or colours.
Category: Artificial Intelligence

[6] viXra:1906.0193 [pdf] submitted on 2019-06-11 07:39:06

People Beat Machines Recognizing Speech

Authors: George Rajna
Comments: 51 Pages.

Humans, on the other hand, are amazingly good at dealing with variations in language. We are so good, in fact, that we really take note when things occasionally break down. [27] A team of British researchers has developed a method that enables computers to make decisions in a way that is more similar to humans. [26] One of the most spectacular facts of the last two centuries of economic history is the exponential growth in GDP per capita in most of the world. Figure 1 shows the rise (and the difference) in living standards for five countries since 1000 AD. [25]
Category: Artificial Intelligence

[5] viXra:1906.0187 [pdf] submitted on 2019-06-11 19:02:36

Enhancements in Audio Ads Delivery and Effectiveness

Authors: RJ Harry
Comments: 2 Pages.

This work details progress in audio ads - delivery and effectiveness. With the increased use of smart speakers and voice-based commands, a new ad avenue in the form of audio ads is rapidly emerging. Audio ads however are different in several aspects from traditional banner/image/video/text (email) ads. For one they’re richer in terms of contextual information as the user interaction with voice is more personal and can be used to determine various aspects from user mood to activity being preformed.
Category: Artificial Intelligence

[4] viXra:1906.0062 [pdf] submitted on 2019-06-04 05:53:21

Bsoft-Ruby/ruby Based Machine Learning(ml)-LLVM-Tcl/Tk Based Analysis of Cryo-em Images Using Mathematical Software in Probing the Nano-Bio Systems – an Interesting Insight Into Ruby/ruby-ML and Tcl/Tk Interfacing in the Context of Electron Microscopy Ima

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication & Simple Suggestion

In this communication the importance of BSOFT-Ruby-LLVM-Tcl/Tk systems based imaging framework to probe Cryo-EM images is presented from a practical implementation point of view. Cryo-EM Technique holds an excellent future.Ruby-LLVM based imaging algorithms could form a powerful informatics framework for researching the challenges arising in the domains of nanotechnology. It is very much useful and important to study the behavior of cross-platform interfacing of existing software tools,fine tuning and adapting them to the domains where the models make bold predictions which could form the basis for the discovery of new nanoscale phenomena. All the methods presented here are also applicable to TEM/SEM/other EM Image Processing tasks as well. Aimed at writing better image processing software directly in Ruby in the near future as Ruby is already a promising tool in medical imaging areas like DICOM and other applications.Ruby also easily interacts with software already developed using C/C++/Java/Tcl/Tk/LLVM with its own extension capabilities.BSOFT, a well established Electron Microscopy Image Processing Software is chosen to experiment with,hence this presentation.
Category: Artificial Intelligence

[3] viXra:1906.0041 [pdf] submitted on 2019-06-05 05:15:15

Computer Make Decision like Humans

Authors: George Rajna
Comments: 49 Pages.

A team of British researchers has developed a method that enables computers to make decisions in a way that is more similar to humans. [26] One of the most spectacular facts of the last two centuries of economic history is the exponential growth in GDP per capita in most of the world. Figure 1 shows the rise (and the difference) in living standards for five countries since 1000 AD. [25] While it is undeniable that AI has opened up a wealth of promising opportunities, it has also led to the emergence of a mindset that can be best described as "AI solutionism". [24]
Category: Artificial Intelligence

[2] viXra:1906.0040 [pdf] submitted on 2019-06-05 05:25:36

Deep Learning Retrosynthesis

Authors: George Rajna
Comments: 41 Pages.

Researchers, from biochemists to material scientists, have long relied on the rich variety of organic molecules to solve pressing challenges. [25] Social, economic, environmental and health inequalities within cities can be detected using street imagery. [24] Citizen science is a boon for researchers, providing reams of data about everything from animal species to distant galaxies. [23] In early 2018, with support from IBM Corporate Citizenship and the Danish Ministry for Foreign Affairs, IBM and the Danish Refugee Council (DRC) embarked on a partnership aimed squarely at the need to better understand migration drivers and evidence-based policy guidance for a range of stakeholders. [22]
Category: Artificial Intelligence

[1] viXra:1906.0024 [pdf] submitted on 2019-06-02 07:58:03

AI the Future of Work and Inequality

Authors: George Rajna
Comments: 48 Pages.

One of the most spectacular facts of the last two centuries of economic history is the exponential growth in GDP per capita in most of the world. Figure 1 shows the rise (and the difference) in living standards for five countries since 1000 AD. [25] While it is undeniable that AI has opened up a wealth of promising opportunities, it has also led to the emergence of a mindset that can be best described as "AI solutionism". [24] Intel's Gadi Singer believes his most important challenge is his latest: using artificial intelligence (AI) to reshape scientific exploration. [23]
Category: Artificial Intelligence