| viXra.org > Artificial Intelligence > 2311 |
 |
 |
| viXra.org > Artificial Intelligence > 2311 |
|
|
[6] viXra:2311.0113 [pdf] submitted on 2023-11-24 02:18:52
Authors: Cadey A. Ratio, Nicole Brennan, Jessica Williams, Ashley Kaplan, Stephanie Williams, Ma Insa
Comments: 4 Pages.
A novel approach to generating fiction novels using a combination of Plotto, a system of plot formulas, and GPT-4, a state-of-the-art language model is presented. An eBook publication pipeline that automates the process of creating and formatting eBooks from the generated text is also described. The aim is to explore the potential and limitations of using artificial intelligence for creative writing, as well as to provide a tool for amusement and experimentation.
Category: Artificial Intelligence
[5] viXra:2311.0089 [pdf] submitted on 2023-11-19 12:03:16
Authors: Nana Abeka Otoo, Asirifi Boa, Muhammad Abubakar
Comments: 7 Pages.
This paper presents a prototype-based soft feature selection package (Sofes) wrapped around the highly interpretable Matrix Robust Soft Learning Vector Quantization (MRSLVQ) and the Local MRSLVQ algorithms. The process of assessing feature relevance with Sofes aligns with a comparable approach established in the Nafes package, with the primary distinction being the utilization of prototype-based induction learners influenced by a probabilistic framework. The numerical evaluation of test results aligns Sofes' performance with that of the Nafes package.
Category: Artificial Intelligence
[4] viXra:2311.0080 [pdf] submitted on 2023-11-16 02:48:07
Authors: Ansh Chaudhary
Comments: 4 Pages.
Deep learning has revolutionized the approach to complex data-driven problems, specifically in medical imaging, where its techniques have significantly raised efficiency in organ segmentation. The urgent need to enhance the depth and precision of organ-based classification is an essential step towards automation of medical operation and diagnostics. The research aims to investigate the effect andpotential advantages transformer models have on binary semantic segmentation, the method utilized for the project. Hence, I employed the SegFormer model, for its lightweight architecture, as the primary deep learning model, alongside the Unet. A custom 2D computerized tomography (CT) scan dataset was assembled, CT-Org2D through meticulous operations. Extensive experiments showed that, in contrast to the selected models, the task’s simplicity required a redesigned Unet architecture with reduced complexity. This model yielded impressive results: Precision,Recall, and IOU scores of 0.91, 0.92, and 0.85 respectively. The research serves as a starting point, motivating further exploration, through different methodologies, to achieve even greater efficiency in organ segmentation.
Category: Artificial Intelligence
[3] viXra:2311.0079 [pdf] submitted on 2023-11-16 11:31:14
Authors: Clifford Njoroge
Comments: 12 Pages. AI music
Music generation is a challenging task that requires capturing the complex and diverse aspects of musical structure and expression. In this paper, we investigate the factors that affect the quality of music generated by various AI models, such as MuseGAN, MuseGAN-Image and GPT3-Music¹[1]. We use different data encoding and processing techniques to create and evaluate music generation models based on generative adversarial networks (GANs) and transformers. We compare the advantages and disadvantages of each method in terms of harmonic, temporal and spatial aspects of music. We identify several challenges and drawbacks of the existing methods, such as harmonic loss, GAN overshooting, chord progression, octave representation, and framework compatibility. We also suggest some possible solutions and future directions for improving music generation with AI.
Category: Artificial Intelligence
[2] viXra:2311.0051 [pdf] submitted on 2023-11-10 01:07:12
Authors: Akira Saito
Comments: 4 Pages. In Japanese (Note by viXra Admin: Please fill in author name in English)
We were able to express the order variables of the spin glassing model in the ground state using simultaneous equations. By similar formula expansion, a formula equivalent to a machine learning perceptron can be obtained. The machine learning perceptron is an empirical form that is the result of trial and error, and there is no basis for formulating it. However, by deriving an equivalent formula by mathematical formula expansion of the spinglassizing model, we have I think the proof has been established. In addition, we believe that creating simultaneous equations will advance machine learning analysis, potentially contributing to reducing learning costs and creating highly accurate models, and contributing to the further penetration of machine learning into various fields.
Category: Artificial Intelligence
[1] viXra:2311.0021 [pdf] replaced on 2025-05-26 09:08:28
Authors: Dimiter Dobrev, George Popov
Comments: 7 Pages.
Our generation is the one that will create the first Artificial Intelligence (AI). We are the ones who will set the rules to which this AI will operate. Once these rules are set, they will be there forever, hence our responsibility is huge. There will be no chance of a second AI because the first one will take control and will not allow the creation of another AI. Our first and foremost concern is not to lose control of the first (and only) AI. Hopefully we will be reasonable enough and not let that happen. However, even if people retain control of AI, the question that comes next is who exactly will those people be? Should they enjoy the absolute power to issue whatever commands to AI they wish? Or should certain restrictions be embedded in AI at its very inception?
Category: Artificial Intelligence
| Third-Party Links: |
|