Data scientist with a strong commitment to solving real-world problems through data. Enthusiastic about starting new projects and acquiring domain knowledge to enhance problem-solving capabilities. Actively participate in competitions to learn from the community and stay competitive. Continuously read research papers to keep up with new developments. Experienced with various data types across different domains, with a particular affinity for computer vision problems
- Created an application that allows users to describe images using their voice, converting the audio input into text with the OpenAI Whisper-1 model, and then generating an image from that text using the DALL-E model. Users can also obtain descriptions of their generated images via GeminiAI. https://github.com/HuseyinBaytar/VisionOfVoice
- For the Teknofest NLP competition, I developed a model with 85% accuracy using only 8MB of data by employing a transformer-encoder architecture with PyTorch to extract sentiment and brand names from Turkish customer reviews. Despite not using a pre-trained model, we ranked 18th out of 90 teams, competing against others who used pre-trained models. https://github.com/we-bears/Turkish-Brand-Entity-Sentiment-Recognizer
- The Carbon Footprint Calculator project is a user-friendly web application designed to empower individuals to assess and understand their environmental impact. https://github.com/HuseyinBaytar/CarbonFootPrintCalculator
- Deep Learning Specialization
- Generative AI & Prompt Engineer
- Professional Data Engineer
- Machine Learning Engineer
- Miuul Datascience Bootcamp(4months)
- IBM Data Science Professional
