Guman Garayev

Mr. Guman Garayev


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 April 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
GGGuman Garayev
Guman Garayev
Azar AliliAzar Alili
Azar Alili
This paper proposes an enhanced Quantum Key Distribution (QKD) protocol by incorporating a Three-Dimensional Angular Momentum Representation (3D AMR) to address vulnerabilities inherent in traditional two-dimensional polarization states-based systems. The 3D AMR method expands the state space, potentially increasing security against sophisticated quantum attacks. We present a theoretical and computational framework that transitions from the conventional two-dimensional polarization to a three-dimensional angular momentum space, which inherently increases the complexity and security of the quantum states used in QKD.

15 July 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
GGGuman Garayev
Guman Garayev
This paper presents an enhanced Fully Connected Neural Network (FCNN) framework that incorporates manifold learning and Renormalization Group (RG) methods. By integrating Christoffel symbols, the model adapts to the curvature and topology of the data manifold, improving learning from geometrically complex data. Additionally, RG methods enable effective multi-scale data processing. We demonstrate the enhanced model’s performance on synthetic and real-world datasets, showing improved accuracy compared to standard FCNNs, particularly in complex systems simulation.

13 August 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
GGGuman Garayev
Guman Garayev
This study introduces a new approach to modeling galaxy rotation curves by integrating concepts from Perelman’s functional with modifications to General Relativity. While initial numerical simulations indicate that our P-E Integration model may offer a closer fit to observed data than existing theories, we recognize the preliminary nature of these findings [14]. The results, though promising, should be interpreted cautiously. Further validation across different galactic systems and refinement of the model are necessary to confirm its broader applicability [15]. This work aims to contribute to the understanding of galactic dynamics, with the hope of opening new avenues for future research.

11 July 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
GGGuman Garayev
Guman Garayev
Azar AliliAzar Alili
Azar Alili
In This paper we introduce the integration of Renormalization Group (RG) methods with Deep Q-Networks (DQNs) to improve reinforcement learning in high-dimensional state spaces. RG methods provide multi-scale analysis, enhancing state representation, learning stability, and exploration. The proposed RG-DQN algorithm uses hierarchical Q-value estimation and multi-scale representations, demonstrating superior performance on synthetic genomic data compared to traditional DQNs.}

23 October 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
GGGuman Garayev
Guman Garayev
Azar AliliAzar Alili
Azar Alili
We propose a SUSY-inspired loss framework to address the generalizationrobustness trade-off in AI. Combining bosonic and fermionic components, the loss ensures smooth learning and robustness against adversarial attacks. Parallel transport stabilizes weight updates across non-Euclidean loss landscapes. Validation on CIFAR-10 demonstrates stable convergence and enhanced performance under FGSM and PGD attacks, confirming the effectiveness of the proposed approach. Keywords: Supersymmetry, Generalization, Robustness, Adversarial Attacks, Parallel Transport, Loss Optimization, CIFAR-10.

26 July 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
GGGuman Garayev
Guman Garayev
Azar AliliAzar Alili
Azar Alili
Generative Adversarial Networks (GANs) are powerful models for generative tasks but face significant challenges such as instability, mode collapse, and inefficient convergence. This paper introduces a theoretical framework leveraging Fermi-Dirac statistics, Ruppeiner geometry, phase transition dynamics, and graph theory to address these issues. The proposed theorems provide a robust mathematical foundation for enhancing GAN stability, diversity, and convergence. Experimental validation on the MNIST dataset demonstrates that the application of these theorems results in improved Inception Scores, reduced Fr´echet Inception Distances, and stable training dynamics, as indicated by Ruppeiner curvature analysis. The findings suggest that these theoretical insights offer a comprehensive solution to the persistent challenges in GAN training, paving the way for more reliable and effective generative models.