Browsing by Author "Batyr Sharimbayev"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Development and optimization ofphysics-informed neural networks for solving partial differential equations
    (SDU University, 2025) Batyr Sharimbayev; Shirali Kadyrov; Aleksei Kavokin
    This study investigates the application of physics-informed neural networks (PINNs) for solving Poissonequations in both 1D and 2D domains and compares them with finite difference method. Additionally, thestudy explores the capability of multi-task learning with PINNs, where the network not only predicts thesolution but also estimates unknown parameters. In the case of a second-order differential equation witha varying coefficient, PINNs successfully approximated both the source term and the varying coefficientwhile achieving low training loss. The model demonstrated excellent generalization capabilities and accuratereconstruction of the underlying system parameters, showing the potential of PINNs in complex physicalsimulations.
  • Thumbnail Image
    ItemOpen Access
    Text Classification for AI Generated Content with Machine Learning and Deep Learning Models
    (5th International Conference on Smart Information Systems and Technologies (SIST), 2025) Batyr Sharimbayev; Shirali Kadyrov
    The rapid development of generative AI models, such as GPT-4, LLaMA, and Gemini, is causing an explosion of AI-generated text that may be akin to human writing. This poses a challenge in differentiating between AI generated content and human-authored text across a range of verticals: academic integrity, misinformation detection, and content moderation. This paper presents a comparison of machine learning and deep learning models on the classifier for AI-generated text. We compare the performance of Logistic Regression with TF-IDF features, a Bi-LSTM model, and a fine-tuned DistilBERT model on data from the COLING Workshop on MGT Detection Task 1, involving text samples from five AI models and human authors. Our experiments showed that Bi-LSTM outperforms other models, yielding the best results in accuracy (90.09%) and F1-score (90.02%). We further present the binary classification performance that distinguishes AI-generated text from human-written content, with an accuracy of 95.9%. It is suggested that deep learning methods are competent in detecting AI-generated text, though there are certain limitations, including adversarial attacks and changing styles of AI-generated writing. Future work will be focused on enhancing model robustness through adversarial training and hybrid architectures.