Artificial Intelligence

1910 Submissions

[17] viXra:1910.0257 [pdf] submitted on 2019-10-15 02:19:06

[ Gentle Compiler Construction System/cool-Spe ] in the Context of [ Minsky Machines/nlp ] Towards Big Data Testing on Iot/hpc [ Hardware+software+firmware ] R&D Platforms – a General Approach in Using Minsky Machines+nlp.

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication & Technical Notes

[ Gentle Compiler Construction System/CooL-SPE ] in the Context of [ Minsky Machines/NLP ] towards BIG DATA Testing on IoT/HPC - [ Hardware+Software+Firmware ] R&D Platforms – A General Approach in Using Minsky Machines+NLP.
Category: Artificial Intelligence

[16] viXra:1910.0255 [pdf] submitted on 2019-10-15 04:07:04

A Deep Neural Network as Surrogate Model for Forward Simulation of Borehole Resistivity Measurements

Authors: M. Shahriari, D. Pardo, B. Moser
Comments: 7 Pages.

Inverse problems appear in multiple industrial applications. Solving such inverse problems require the repeated solution of the forward problem. This is the most time-consuming stage when employing inversion techniques, and it constitutes a severe limitation when the inversion needs to be performed in real-time. In here, we focus on the real-time inversion of resistivity measurements for geosteering. We investigate the use of a deep neural network (DNN) to approximate the forward function arising from Maxwell's equations, which govern the electromagnetic wave propagation through a media. By doing so, the evaluation of the forward problems is performed offline, allowing for the online real-time evaluation (inversion) of the DNN.
Category: Artificial Intelligence

[15] viXra:1910.0242 [pdf] submitted on 2019-10-14 13:56:34

An Empirical Study of Active Learning Strategies for Supervised Classification

Authors: Louis Desreumaux
Comments: 81 Pages. Language : french

Modern supervised learning methods are known to require large amounts of training examples to reach their full potential. Since these examples are mainly obtained through human experts who manually label samples, the labeling process may have a high cost. Active learning aims to reduce annotation cost by predicting which samples are useful for a human expert to label. Although this field is quite old, several important challenges to using active learning in real-world settings still remain unsolved. In particular, most selection strategies are hand-designed, and it has become clear that there is no best active learning strategy. This has motivated research into meta-learning algorithms for "learning how to actively learn". In this report, a comprehensive comparison of active learning strategies is presented, including a strategy learnt using reinforcement learning.
Category: Artificial Intelligence

[14] viXra:1910.0234 [pdf] submitted on 2019-10-14 03:51:15

The Pascal Triangle of Maximum Deng Entropy

Authors: Xiaozhuan Gao, Yong Deng
Comments: 19 Pages.

Pascal-Triangle (known as Yang Hui Triangle) is an important structure in mathematics, which has been used many fields. Entropy plays an essential role in physics. In various, information entropy is used to measure the uncertainty of information. Hence, setting the connection between Pascal Triangle and information uncertainty is a question worth exploring. Deng proposed the Deng entropy that it can measure non-specificity and discord of basic probability assignment (BPA) in Dempster-Shafer (D-S) evidence theory. D-S evidence theory and power set are very closely related. Hence, by analysing the maximum Deng entropy, the paper find that there is an potential rule of BPA with changes of frame of discernment. Finally, the paper set the relation between the maximum Deng entropy and PascalTriangle.
Category: Artificial Intelligence

[13] viXra:1910.0197 [pdf] submitted on 2019-10-12 21:56:48

[ OCaml-LLVM/Polly-Owl-Satallax(Theorem Prover in OCaml) - CoqTP/OCaml - Q*cert/OCaml/Eigen ] in the Context of IoT/HPC-High Performance Computing - Heterogeneous Environments to [ Design+Test+Implement DNA based Theoretical Gene Therapy Informatics ] R&D

Authors: Nirmal Tej Kumar
Comments: 4 Pages. Short Communication & Technical Notes

[ OCaml-LLVM/Polly-Owl-Satallax(Theorem Prover in OCaml) - CoqTP/OCaml - Q*cert/OCaml/Eigen ] in the Context of IoT/HPC-High Performance Computing - Heterogeneous Environments to[Design+Test+Implement DNA based Theoretical Gene Therapy Informatics ] R&D Framework – A Simple Suggestion & Novel Approach.
Category: Artificial Intelligence

[12] viXra:1910.0191 [pdf] submitted on 2019-10-12 03:54:59

Artificial Intelligence Determine Exoplanets Sizes

Authors: George Rajna
Comments: 40 Pages.

Using a machine learning technique, a team of Instituto de Astrofísica e Ciências do Espaço researchers constrained the radius of an exoplanet with known mass. [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

[11] viXra:1910.0166 [pdf] submitted on 2019-10-10 16:35:34

Unbias Coding(™): a Meditation.

Authors: Bheemaiah, Anil Kumar
Comments: 4 Pages.

The blue ribbon of free speech was taunted, may be it is the Unbias Coding(™) by A.B, my company. ChatterBoxing with the network, I meditate in this publication on OOPS, NLP and the wigner universe, can we evolve self conscious machines, without the diagonal paradox? Read my reflections and share yours at the miyawaki spam free mail address. Keywords: Approximation, iSense, metamodels, machine evolution, code generation, OOPS, NLP, Cheap Talk, Sand Boxing, Wolfram Cloud and Script, Wisdom Capital.
Category: Artificial Intelligence

[10] viXra:1910.0163 [pdf] submitted on 2019-10-10 01:52:58

[ Julia+flux-ML Library+polly-LLVM+QRNG Services/quantum Devices+qrng Library ] in the Context of Understanding [ Machine Learning-Ml/internet of Things-Iot/hpc High Performance Computing ] Based Advanced Medical Imaging Software R&D

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

[ Julia+Flux-ML Library+Polly-LLVM+QRNG Services/Quantum Devices+qrng library ] in the Context of Understanding [ Machine Learning-ML/Internet of Things-IoT/HPC -High Performance Computing ] based Advanced Medical Imaging Software R&D – A Simple & Useful Suggestion.
Category: Artificial Intelligence

[9] viXra:1910.0122 [pdf] replaced on 2019-10-10 13:39:04

Confusion in the Matrix: Going Beyond the Roc Curve

Authors: Stephen Borstelmann, Saurabh Jha
Comments: 12 Pages. Spelling corrections, improved image quality, minor additions.

Artificial intelligence algorithms are being created both investigationally and commercially. Evaluation of their performance is important for developers, investigators, clinical physicians, and regulatory agencies. No clear consensus exists on what metrics are best for algorithmic evaluation for AI and ML applications in radiology. We review the basics of the confusion matrix, continue to single number summary values such as accuracy, F1 score, and ɸ coefficient, and then discuss Receiver Operator Curves and their derivatives, Precision Recall Curves, and Cost Curves. Recommendations are made for potential future directions and what currently may be best practices in algorithmic evaluation metrics.
Category: Artificial Intelligence

[8] viXra:1910.0108 [pdf] submitted on 2019-10-08 09:17:39

Artificial Intelligence Cytometer in Blood

Authors: George Rajna
Comments: 42 Pages.

Detection of rare cells in blood and other bodily fluids has numerous important applications including diagnostics, monitoring disease progression and evaluating immune response. [25] But making those quantum leaps from science fiction to reality required hard work from computer scientists like Yoshua Bengio, Geoffrey Hinton and Yann LeCun. [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

[7] viXra:1910.0101 [pdf] submitted on 2019-10-07 09:42:55

[ JI Prolog/JikesRVM-Research Virtual Machine/Java-NLP/Java-Genetic Algorithms ] & its Important Uses in the R&D Domains of [ Bio-informatics ] – A Simple Suggestion Once Again in the Context of Complex Systems by Adding Java based AI Dimension.

Authors: Nirmal Tej Kumar
Comments: 4 Pages. Short Communication & Technical Notes

[ JI Prolog/JikesRVM-Research Virtual Machine/Java-NLP/Java-Genetic Algorithms ] & its Important Uses in the R&D Domains of [ Bio-informatics ] – A Simple Suggestion Once Again in the Context of Complex Systems by Adding Java based AI Dimension.
Category: Artificial Intelligence

[6] viXra:1910.0087 [pdf] submitted on 2019-10-06 21:42:02

An Insight Into [ Dlib C++ Machine Learning Library + Pulseseq+cplusplus-NLP-Library/python NLTK Library ] Software to Understand MR Sequences in the Context of [ Iot/hpc/nlp ] Informatics Environments.

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication & Technical Notes

An Insight into [ Dlib C++ Machine Learning Library + PulseSeq+CPlusPlus-NLP-Library/python NLTK library ]Software to Understand MR Sequences in the Context of [ IoT/HPC/NLP ] Informatics Environments.
Category: Artificial Intelligence

[5] viXra:1910.0066 [pdf] submitted on 2019-10-06 09:27:07

Breaking the Wall of Unfamiliarity of One's Own Voice

Authors: Sun Ruikang
Comments: 2 Pages.

The voice someone heard inside their head is generally different from it heard on record. This problem makes it difficult to sing correctly for many people. Due to the development of Transfer Learning and Neural Networks, we can transfer the voice we really made to the voice we intend to with models like Generative Adversarial Networks (GAN).
Category: Artificial Intelligence

[4] viXra:1910.0060 [pdf] submitted on 2019-10-05 14:14:25

Study on Application of Machine Learning Intelligence for Identification and Control of Nonlinear Dynamical Systems: Case Study Robotic Manipulators

Authors: Divya Rao Ashok Kumar, Krishna Vijayaraghavan
Comments: 50 Pages.

In the literature, machine learning has been referred to as deeply structured learning, hierarchical learning and feature based learning which can provide computational models from high-level data abstractions. One of the most used learning structures is the multiple-layered models of inputs, commonly known as neural networks, which comprise multiple levels of non-linear operations. The machine learning algorithms are able solve many problems around fault detection, isolation and recovery. There has been a growing interest in using learning architectures in advanced robotics applications, e.g., object detection, scene semantic segmentation, and grasping. The real-time learning of high-dimensional features for robotics applications via machine learning techniques is another important topic. In addition, other topics in robotics such as obstacle detection and context-dependent social mapping are also being addressed by researchers through machine learning methods. Machine learning algorithms provide real time driving decisions for automated vehicles (self-driving vehicles or driverless cars) from integration of numerous sensors onboard the vehicle. The advancement of autonomous navigation and situational awareness systems adapt neural networks for analyzing the multi-modal sensor inputs. We observe that machine learning algorithms influence largely in decision making process. But, there is need to understand the control system consequences for adapting the outcome of the machine learning algorithm. This proposal presents the detailed study on the influences of machine learning architectures and algorithms for modeling and control of nonlinear dynamical system. Research Outcome: · Knowledge on machine learning architectures (Support Vector Machines (SVMs), Conditional Random Field, supervised neural network) · Understanding the constraints on applicability of ML architectures for nonlinear dynamical system · Study on real time control of nonlinear dynamical system with ML algorithm in closed loop.
Category: Artificial Intelligence

[3] viXra:1910.0046 [pdf] submitted on 2019-10-05 05:49:58

Machine Learning Cosmic and Subatomic Scales

Authors: George Rajna
Comments: 41 Pages.

While high-energy physics and cosmology seem worlds apart in terms of sheer scale, physicists and cosmologists at Argonne are using similar machine learning methods to address classification problems for both subatomic particles and galaxies. [27] A new study from the U.S. Department of Energy's (DOE) Argonne National Laboratory has achieved a breakthrough in the effort to mathematically represent how water behaves. [26] A new tool is drastically changing the face of chemical research – artificial intelligence. In a new paper published in Nature, researchers review the rapid progress in machine learning for the chemical sciences. [25]
Category: Artificial Intelligence

[2] viXra:1910.0019 [pdf] submitted on 2019-10-01 19:06:48

A Harmless Wireless Quantum Alternative to Cell Phones Based on Quantum Noise

Authors: Robert Neil Boyd, Victor Christianto, Florentin Smarandache
Comments: 5 Pages. This paper has been accepted and published by EC Neurology Journal, 2019. Comments are welcome

In the meantime we know that 4G and 5G technologies cause many harms to human health. Therefore, here we submit a harmless wireless quantum alternative to cell phones. It is our hope that this alternative communication method can find its way to realization, while the existing RF based wireless technologies (4G, 5G) are being phased out.
Category: Artificial Intelligence

[1] viXra:1910.0009 [pdf] submitted on 2019-10-01 01:35:41

[ Python Metaprogramming+Z3Py-Python Theorem Prover+ImageAI ] in the Context of Radiation Oncology & [ IoT/HPC ]- High Performance Computing Heterogeneous Informatics R&D – An Interesting Insight into the World of Metaprogramming Concepts

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication-Review

[ Python Metaprogramming+Z3Py-Python Theorem Prover+ImageAI ] in the Context of Radiation Oncology & [ IoT/HPC ]- High Performance Computing Heterogeneous Informatics R&D – An Interesting Insight into the World of Metaprogramming Concepts With a Useful Review. [ Exploring Metaprogramming+AI to Probe Complex Design Patterns Next Generation Medical Software R&D ]
Category: Artificial Intelligence