| viXra.org > Artificial Intelligence > 2108 |
 |
 |
| viXra.org > Artificial Intelligence > 2108 |
|
|
[10] viXra:2108.0169 [pdf] submitted on 2021-08-31 12:44:04
Authors: Amey Thakur, Mega Satish
Comments: 19 pages, 23 figures, Volume 9, Issue VIII, International Journal for Research in Applied Science and Engineering Technology (IJRASET), 2021. DOI: https://doi.org/10.22214/ijraset.2021.37723
Deep learning's breakthrough in the field of artificial intelligence has resulted in the creation of a slew of deep learning models. One of these is the Generative Adversarial Network, which has only recently emerged. The goal of GAN is to use unsupervised learning to analyse the distribution of data and create more accurate results. The GAN allows the learning of deep representations in the absence of substantial labelled training information. Computer vision, language and video processing, and image synthesis are just a few of the applications that might benefit from these representations. The purpose of this research is to get the reader conversant with the GAN framework as well as to provide the background information on Generative Adversarial Networks, including the structure of both the generator and discriminator, as well as the various GAN variants along with their respective architectures. Applications of GANs are also discussed with examples.
Category: Artificial Intelligence
[9] viXra:2108.0155 [pdf] submitted on 2021-08-27 21:01:29
Authors: Yew Kee Wong
Comments: 9 Pages.
In the information era, enormous amounts of data have become available on hand to decision makers. Big data refers to datasets that are not only big, but also high in variety and velocity, which makes them difficult to handle using traditional tools and techniques. Due to the rapid growth of such data, solutions need to be studied and provided in order to handle and extract value and knowledge from these datasets. Machine learning is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make
decisions with minimal human intervention. Such minimal human intervention can be provided using machine learning, which is the application of advanced deep learning techniques on big data. This paper aims to analyse some of the different machine learning and deep learning algorithms and methods, as
well as the opportunities provided by the AI applications in various decision making domains.
Category: Artificial Intelligence
[8] viXra:2108.0154 [pdf] submitted on 2021-08-27 21:02:30
Authors: Yew Kee Wong
Comments: 8 Pages.
Artificial intelligence has been an eye-popping word that is impacting every industry in the world. With the rise of such advanced technology, there will be always a question regarding its impact on our social life, environment and economy thus impacting all efforts exerted towards continuous development. From the definition, the welfare of human beings is the core of continuous development. Continuous development is useful only when ordinary people’s lives are improved whether in health, education, employment, environment, equality or justice. Securing decent jobs is a key enabler to promote the components of continuous development, economic growth, social welfare and environmental sustainability. The human resources are the precious resource for nations. The high unemployment and underemployment rates especially in youth is a great threat affecting the continuous economic development of many countries and is influenced by investment in education, and quality of living.
Category: Artificial Intelligence
[7] viXra:2108.0153 [pdf] submitted on 2021-08-27 21:04:08
Authors: Yew Kee Wong
Comments: 6 Pages.
The assessment outcome for many online learning methods are based on the number of correct answers and than convert it into one final mark or grade. We discovered that when using online learning, we can extract more detail information from the learning process and these information are useful for the assessor to plan an effective and efficient learning model for the learner. Statistical analysis is an
important part of an assessment when performing the online learning outcome. The assessment
indicators include the difficulty level of the question, time spend in answering and the variation in choosing answer. In this paper we will present the findings of these assessment indicators and how it can improve the way the learner being assessed when using online learning system. We developed a statistical analysis algorithm which can assess the online learning outcomes more effectively using
quantifiable measurements. A number of examples of using this statistical analysis algorithm are presented.
Category: Artificial Intelligence
[6] viXra:2108.0152 [pdf] submitted on 2021-08-27 21:05:13
Authors: Yew Kee Wong
Comments: 8 Pages.
In the information era, enormous amounts of data have become available on hand to decision makers. Big data refers to datasets that are not only big, but also high in volume, velocity, variety and veracity (the four V’s of big data), which makes them difficult to handle using traditional tools and techniques. Due to the rapid growth of such data, solutions need to be studied and provided in order to handle and extract value and knowledge from these datasets. Furthermore, decision makers need to be able to gain valuable insights from such varied and rapidly changing data, ranging from daily transactions to customer interactions and social network data. Such value can be provided using big data analytics, which is the application of advanced analytics techniques on big data. This paper aims to analyse some
of the use of big data for the artificial intelligence development and its applications in various decision making domains.
Category: Artificial Intelligence
[5] viXra:2108.0147 [pdf] submitted on 2021-08-25 23:16:30
Authors: Jeongik Cho
Comments: 10 Pages.
Generators in generative adversarial networks map latent distributions into data distributions. GAN inversion is mapping data distribution to latent distribution by inverting the generator of GAN.
In this paper, I introduce a direction embedding discriminator GAN in which the discriminator learns the inverse mapping of the generator. In the suggested method, when the latent vector is sampled from an i.i.d. (independent and identically distributed) random variable, the latent vector is considered as angular coordinates of spherical coordinates. Thus, the latent vector can be transformed into a point on the surface of the hypersphere in cartesian coordinates.
Discriminator embeds the generated data point into cartesian coordinates. The direction of embedded coordinates represents predicted cartesian coordinates of latent vector, and the log of magnitude represents an adversarial value (real/fake). The generator and discriminator are trained cooperative to decrease the angle between the embedded cartesian coordinates from the discriminator and the cartesian coordinates converted from the latent vector considered as angular coordinates of spherical coordinates. The suggested method can be applied during GAN training, does not require additional encoder training, and does not use a reconstruction loss.
Category: Artificial Intelligence
[4] viXra:2108.0130 [pdf] submitted on 2021-08-24 11:26:13
Authors: Amey Thakur, Archit Konde
Comments: 22 pages, 15 figures, Volume 9, Issue VIII, International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2021. DOI: http://dx.doi.org/10.22214/ijraset.2021.37362
The purpose of this study is to familiarise the reader with the foundations of neural networks. Artificial Neural Networks (ANNs) are algorithm-based systems that are modelled after Biological Neural Networks (BNNs). Neural networks are an effort to use the human brain's information processing skills to address challenging real-world AI issues. The evolution of neural networks and their significance are briefly explored. ANNs and BNNs are contrasted, and their qualities, benefits, and disadvantages are discussed. The drawbacks of the perceptron model and their improvement by the sigmoid neuron and ReLU neuron are briefly discussed. In addition, we give a bird's-eye view of the different Neural Network models. We study neural networks (NNs) and highlight the different learning approaches and algorithms used in Machine Learning and Deep Learning. We also discuss different types of NNs and their applications. A brief introduction to Neuro-Fuzzy and its applications with a comprehensive review of NN technological advances is provided.
Category: Artificial Intelligence
[3] viXra:2108.0120 [pdf] submitted on 2021-08-23 13:14:27
Authors: Mirzakhmet Syzdykov
Comments: 5 Pages.
In this work we present the theoretical approach over solving the back-reference problem in
regular expression matching within the almost polynomial time using local search within the memory, while
within the growth of capturing groups we obtain the exponential results: for this purpose we develop the
modified matching algorithm operating on non-deterministic finite automata within the modified search
algorithm and presence of the specific method also over extended regular expressions. This is made due to
the algorithm which can be adjusted for approximate searching allowing us to imply extended operators and
features of modern regular expressions like intersection, subtraction and complement, as well as backreferences. The review of past work on this issues is also done: to the present time there is no discrete
algorithm in systems like automata for local search. Thus, we obtain the new result of matching the pattern
locally while the simulating algorithm works as usual. The obtained result also refers to the membership
problem with local bound which can be set in the main algorithm presented in this article.
Category: Artificial Intelligence
[2] viXra:2108.0095 [pdf] submitted on 2021-08-18 23:35:38
Authors: Shiyou Lian
Comments: Pages.
Starting from finding approximate value of a function, introduces the measure of approximation-degree between two numerical values, proposes the concepts of “strict approximation” and “strict approximation region”, then, derives the corresponding one-dimensional interpolation methods and formulas, and then presents a calculation model called “sum-times-difference formula” for high-dimensional interpolation, thus develops a new interpolation approach, that is, ADB interpolation. ADB interpolation is applied to the interpolation of actual functions with satisfactory results. Viewed from principle and effect, the interpolation approach is of novel idea, and has the advantages of simple calculation, stable accuracy, facilitating parallel processing, very suiting for high-dimensional interpolation, and easy to be extended to the interpolation of vector valued functions. Applying the approach to instance-based learning, a new instance-based learning method, learning using ADB interpolation, is obtained. The learning method is of unique technique, which has also the advantages of definite mathematical basis, implicit distance weights, avoiding misclassification, high efficiency, and wide range of applications, as well as being interpretable, etc. In principle, this method is a kind of learning by analogy, which and the deep learning that belongs to inductive learning can complement each other, and for some problems, the two can even have an effect of “different approaches but equal results” in big data and cloud computing environment. Thus, the learning using ADB interpolation can also be regarded as a kind of “wide learning” that is dual to deep learning.
Category: Artificial Intelligence
[1] viXra:2108.0029 [pdf] replaced on 2021-12-28 16:57:48
Authors: Ait-Taleb Nabil
Comments: 34 Pages.
In this paper, we are proposing a learning algorithm for continuous data matrix based on entropy absorption of a Bayesian network.This method consists in losing a little bit of likelihood compared to a chain rule's best likelihood, in order to get a good idea of the higher conditionings that are taking place between the Bayesian network's nodes. We are presenting the known results related to information theory, the multidimensional Gaussian probability, AIC and BIC scores for continuous data matrix learning from a Bayesian network, and we are showing the entropy absorption algorithm using the Kullback-leibler divergence with an example of continuous data matrix.
Category: Artificial Intelligence
| Third-Party Links: |
|