Artificial Intelligence

1608 Submissions

[7] viXra:1608.0291 [pdf] submitted on 2016-08-24 01:48:59

A Comparison of the Generalized minC Combination and the Hybrid DSm Combination Rules

Authors: Milan Daniel
Comments: 18 Pages.

A generalization of the minC combination to DSm hyper-power sets is presented. Both the special formulas for static fusion or dynamic fusion without non-existential constraints and the quite general formulas for dynamic fusion with non-existential constraints are included. Examples of the minC combination on several different hybrid DSm models are presented. A comparison of the generalized minC combination with the hybrid DSm rule is discussed and explained on examples.
Category: Artificial Intelligence

[6] viXra:1608.0224 [pdf] submitted on 2016-08-20 12:45:56

Search for Dynamical Origin of Social Networks

Authors: Michail Zak
Comments: 33 Pages.

The challenge of this work is to re-define the concept of intelligent agent as a building block of social networks by presenting it as a physical particle with additional non-Newtonian properties. The proposed model of an intelligent agent described by a system of ODE coupled with their Liouville equation has been introduced and discussed. Following the Madelung equation that belongs to this class, non-Newtonian properties such as superposition, entanglement, and probability interference typical for quantum systems have been described. Special attention was paid to the capability to violate the second law of thermodynamics, which makes these systems neither Newtonian, nor quantum. It has been shown that the proposed model can be linked to mathematical models of livings as well as to models of AI. The model is presented in two modifications. The first one is illustrated by the discovery of a stochastic attractor approached by the social network; as an application, it was demonstrated that any statistics can be represented by an attractor of the solution to the corresponding system of ODE coupled with its Liouville equation. It was emphasized that evolution to the attractor reveals possible micro-mechanisms driving random events to the final distribution of the corresponding statistical law. Special attention is concentrated upon the power law and its dynamical interpretation: it is demonstrated that the underlying micro- dynamics supports a “violent reputation” of the power-law statistics. The second modification of the model of social network associated with a decision-making process and applied to solution of NP-complete problems known as being unsolvable neither by classical nor by quantum algorithms. The approach is illustrated by solving a search in unsorted database in polynomial time by resonance between external force representing the address of a required item and the response representing the location of this item.
Category: Artificial Intelligence

[5] viXra:1608.0187 [pdf] submitted on 2016-08-18 14:02:36

Neuromorphic Architecture

Authors: George Rajna
Comments: 28 Pages.

In the future, level-tuned neurons may help enable neuromorphic computing systems to perform tasks that traditional computers cannot, such as learning from their environment, pattern recognition, and knowledge extraction from big data sources. [19] IBM scientists have created randomly spiking neurons using phase-change materials to store and process data. This demonstration marks a significant step forward in the development of energy-efficient, ultra-dense integrated neuromorphic technologies for applications in cognitive computing. [18] An ion trap with four segmented blade electrodes used to trap a linear chain of atomic ions for quantum information processing. Each ion is addressed optically for individual control and readout using the high optical access of the trap. [17] To date, researchers have realised qubits in the form of individual electrons ( However, this led to interferences and rendered the information carriers difficult to programme and read. The group has solved this problem by utilising electron holes as qubits, rather than electrons. [16] Physicists from MIPT and the Russian Quantum Center have developed an easier method to create a universal quantum computer using multilevel quantum systems (qudits), each one of which is able to work with multiple "conventional" quantum elements – qubits. [15] Precise atom implants in silicon provide a first step toward practical quantum computers. [14] A method to produce significant amounts of semiconducting nanoparticles for light-emitting displays, sensors, solar panels and biomedical applications has gained momentum with a demonstration by researchers at the Department of Energy's Oak Ridge National Laboratory. [13] A source of single photons that meets three important criteria for use in quantum-information systems has been unveiled in China by an international team of physicists. Based on a quantum dot, the device is an efficient source of photons that emerge as solo particles that are indistinguishable from each other. The researchers are now trying to use the source to create a quantum computer based on "boson sampling". [11] With the help of a semiconductor quantum dot, physicists at the University of Basel have developed a new type of light source that emits single photons.
Category: Artificial Intelligence

[4] viXra:1608.0093 [pdf] submitted on 2016-08-08 22:08:41

Edge Based Grid Super-Imposition for Crowd Emotion Recognition

Authors: Amol S Patwardhan
Comments: 6 Pages.

Numerous automatic continuous emotion detection system studies have examined mostly use of videos and images containing individual person expressing emotions. This study examines the detection of spontaneous emotions in a group and crowd settings. Edge detection was used with a grid of lines superimposition to extract the features. The feature movement in terms of movement from the reference point was used to track across sequences of images from the color channel. Additionally the video data capturing was done on spontaneous emotions invoked by watching sports events from group of participants. The method was view and occlusion independent and the results were not affected by presence of multiple people chaotically expressing various emotions. The edge thresholds of 0.2 and grid thresholds of 20 showed the best accuracy results. The overall accuracy of the group emotion classifier was 70.9%.
Category: Artificial Intelligence

[3] viXra:1608.0092 [pdf] submitted on 2016-08-08 22:15:06

Human Activity Recognition Using Temporal Frame Decision Rule Extraction

Authors: Amol Patwardhan
Comments: 4 Pages.

Activities of humans and their recognition has many practical and real world applications such as safety, security, surveillance, humanoid assistive robotics and intelligent simulation systems. Numerous human action and emotion recognition systems included analysis of position and geometric features and gesture based co-ordinates to detect actions. There exits additional data and information in the movement and motion based features and temporal and time-sequential series of image and video frames which can be leveraged to detect and extract a certain actions, postures, gestures and expressions. This paper uses dynamic, temporal, time-scale dependent data to compare with decision rules and templates for activity recognition. The human shape boundaries and silhouette is extracted using geometric co-ordinate and centroid model across multiple frames. The extracted shape boundary is transformed to binary state using eigen space mapping and parameter dependent canonical transformation in 3D space dimension. The image blob data frames are down sampled using activity templates to a single candidate reference frame. This candidate frame was compared with the decision rule driven model to associate with an activity class label. The decision rule driven and activity templates method produced 64% recognition accuracy indicating that the method was feasible for recognizing human activities.
Category: Artificial Intelligence

[2] viXra:1608.0076 [pdf] submitted on 2016-08-08 02:57:31

Watson Doctor

Authors: George Rajna
Comments: 19 Pages.

Watson correctly diagnoses woman after doctors were stumped. [12] The artificial intelligence system's ability to set itself up quickly every morning and compensate for any overnight fluctuations would make this fragile technology much more useful for field measurements, said co-lead researcher Dr Michael Hush from UNSW ADFA. [11] Quantum physicist Mario Krenn and his colleagues in the group of Anton Zeilinger from the Faculty of Physics at the University of Vienna and the Austrian Academy of Sciences have developed an algorithm which designs new useful quantum experiments. As the computer does not rely on human intuition, it finds novel unfamiliar solutions. [10] Researchers at the University of Chicago's Institute for Molecular Engineering and the University of Konstanz have demonstrated the ability to generate a quantum logic operation, or rotation of the qubit, that-surprisingly—is intrinsically resilient to noise as well as to variations in the strength or duration of the control. Their achievement is based on a geometric concept known as the Berry phase and is implemented through entirely optical means within a single electronic spin in diamond. [9] New research demonstrates that particles at the quantum level can in fact be seen as behaving something like billiard balls rolling along a table, and not merely as the probabilistic smears that the standard interpretation of quantum mechanics suggests. But there's a catch-the tracks the particles follow do not always behave as one would expect from "realistic" trajectories, but often in a fashion that has been termed "surrealistic." [8] Quantum entanglement—which occurs when two or more particles are correlated in such a way that they can influence each other even across large distances—is not an all-or-nothing phenomenon, but occurs in various degrees. The more a quantum state is entangled with its partner, the better the states will perform in quantum information applications. Unfortunately, quantifying entanglement is a difficult process involving complex optimization problems that give even physicists headaches. [7] A trio of physicists in Europe has come up with an idea that they believe would allow a person to actually witness entanglement. Valentina Caprara Vivoli, with the University of Geneva, Pavel Sekatski, with the University of Innsbruck and Nicolas Sangouard, with the University of Basel, have together written a paper describing a scenario where a human subject would be able to witness an instance of entanglement—they have uploaded it to the arXiv server for review by others. [6] The accelerating electrons explain not only the Maxwell Equations and the Special Relativity, but the Heisenberg Uncertainty Relation, the Wave-Particle Duality and the electron's spin also, building the Bridge between the Classical and Quantum Theories. The Planck Distribution Law of the electromagnetic oscillators explains the electron/proton mass rate and the Weak and Strong Interactions by the diffraction patterns. The Weak Interaction changes the diffraction patterns by moving the electric charge from one side to the other side of the diffraction pattern, which violates the CP and Time reversal symmetry. The diffraction patterns and the locality of the self-maintaining electromagnetic potential explains also the Quantum Entanglement, giving it as a natural part of the relativistic quantum theory.
Category: Artificial Intelligence

[1] viXra:1608.0041 [pdf] submitted on 2016-08-04 08:00:47

Combining Infinity Number Of Neural Networks Into One

Authors: Bo Tian
Comments: 17 Pages.

One of the important aspects of a neural network is its generalization property, which is measured by its ability to make correct prediction on unseen samples. One option to improve generalization is to combine results from multiple networks, which is unfortunately a time-consuming process. In this paper, a new approach is presented to combine infinity number of neural networks in analytic way to produce a small, fast and reliable neural network.
Category: Artificial Intelligence