With over 3 years of experience in Information Technologies and more than 1 year in Data Science and Machine Learning, I possess a solid understanding of Machine Learning principles, including supervised and unsupervised learning, classification, regression, and clustering algorithms. I am familiar with Deep Learning architectures such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), and their applications in areas like computer vision and natural language processing. I have knowledge of data preprocessing techniques, feature engineering, model selection, and evaluation metrics.

📫 How to reach me: [email protected]

• Python/C++ languages
• SQL, PostgreSQL, Git
• Pandas, NumPy, Scikit-learn, TensorFlow, Matplotlib, Seaborn, XGBoost
• GitHub/GitLab

• Neural Network from scratch - Designed and implemented a neural network framework from scratch, including forward and backward propagation, various activation functions, and optimization algorithms, to enhance understanding of neural network mechanics and gain practical implementation experience.
• Face mood recognition - Developed a facial emotion recognition system using TensorFlow. Preprocessed a dataset of facial images with annotated emotions. Built and trained a convolutional neural network (CNN) to extract features and classify emotions, leveraging transfer learning and fine-tuning techniques for improved accuracy.
• Flood Prediction Competition on Kaggle - I participated in the Flood Prediction Competition on Kaggle, applying machine learning techniques to predict the probability of flooding using historical weather data, terrain features, and other factors. I utilized data exploration, cleaning, and feature engineering to extract meaningful insights and enhance model performance. This experience honed my skills in working with real-world data, applying advanced machine learning techniques, and contributing to a critical societal issue - flood prediction.
• Yolo-based dog breed detection and classification system - In this project, I have developed a system to classify and detect dog breeds in images. Using the YOLO model for dog detection, I have implemented data preprocessing, augmentation, and visualization techniques. The project involves filtering, resizing images, and bounding boxes, as well as preparing data for training models. The workflow is documented, including scripts for data handling and model training. This provides a comprehensive solution for dog breed recognition and detection.