Artificial Intelligence

1906 Submissions

[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