During my studies, I systematically explored artificial neural network theory and developed a strong foundation in machine learning concepts. I also contributed to an experimental research project in an Artificial Neural Network Laboratory, where my work included literature retrieval, dataset cleaning, exploratory analysis, and statistical processing with SPSS and Python. These experiences strengthened my research habits, logical reasoning, attention to detail, and ability to communicate effectively within a project team.
Profile
Academic interests & approachSelected Projects
PortfolioAdaptive Feature Encoding for Small-Sample Neural Classifiers
2024A study of feature normalization and compact neural architectures for classification tasks with limited training data. I focused on literature synthesis, dataset preparation, and comparative analysis.
Comparative Study of Activation Functions in Feedforward Networks
2023–24An experimental comparison of commonly used activation functions, examining training behavior and classification performance across controlled datasets.
Student Learning Dataset: Statistical Pattern Analysis
2023Prepared and analyzed a structured educational dataset, including missing-value treatment, descriptive statistics, variable screening, and interpretation of relationships among study-related measures.
Literature Map of Deep Neural Network Optimization Methods
2022–23Built a structured review of optimization approaches used in neural network training, organizing findings by algorithm family, training objective, and reported experimental setting.
Research Experience
Laboratory projectStudent Research Assistant - Experimental Project
Supported an experimental research workflow through academic literature searches, source organization, dataset cleaning, descriptive statistics, and Python/SPSS-based analysis. Maintained reproducible notes and communicated intermediate findings during team discussions.
Artificial Neural Network Theory
Systematically studied perceptrons, multilayer networks, backpropagation, loss functions, optimization, regularization, and evaluation methodology, with emphasis on connecting mathematical concepts to experimental practice.
Research Toolkit
Working knowledgePythonData preparation, analysis, experiments
SPSSDescriptive & statistical analysis
Neural NetworksTheory, training, evaluation
ResearchLiterature search & synthesis