Artificial Intelligence • Machine Learning • Deep Learning • Generative AI/Large Language Model Enthusiast
Modern neural network & transformer architectures, applied sequence & vision modeling, and reproducible experimentation.
From traditional to advanced; yes, I learn it all.
“Future belongs to the dedicated and the consistent one.”
- Large Language Models & Transformer Spectrum: BERT / RoBERTa (encoder), GPT (decoder), T5 / BART (encoder–decoder), distilled / compact models (DistilBERT, ALBERT). Currently learning parameter‑efficient methods (prompting) and simple RAG setups (testing chunk sizes + embedding choices).
- Traditional Machine Learning Foundations: Support Vector Machine, K-Nearest Neighbor, Regression Models (Linear, Multiple, Logistic), Decision Trees, Random Forest, etc. I still use these for baselines before moving to deep learning/generative AI models.
- Deep Learning Practice:
- Computer Vision: Image classification tasks (CNN), object detection (YOLO), augmentations (Keras), annotations (Roboflow), transfer learning on data
- Neural Network architecture in general
- Sequence Modeling: RNN, LSTM, BiLSTM, GRU, Bidirectional GRU (Sentiment analysis, recommendation system, summarization, etc)
- Transfer Learning: Freezing layers, fine-tuning on datasets
- Ensemble Learning: Averaging / voting and basic stacking
- Model Efficiency & Evaluation
- Applied NLP & Automation: Chatbot prototypes Telegram/WhatsApp), simple knowledge delivery flows.
- Reproducibility: organized folders, requirements pinning, Git versioning. Using GCP occasionally for running heavier notebooks.
| Domain | Tools / Frameworks |
|---|---|
| Languages | Python · C++ (Data Structure) · R (Secondary, Statistic Purpose) |
| Deep Learning | PyTorch · TensorFlow · Scikit-learn · Keras |
| LLM / NLP | Hugging Face Transformers |
| Deployment / Serving | FastAPI (learning) · Docker · Kubernetes |
| Cloud | Google Cloud Platform (Compute/Storage) |
| Experimentation | Jupyter · Git |
| Paradigms | Transfer Learning · Ensemble Learning · Sequence Modeling (RNN / LSTM / GRU) · Computer Vision |
| Classic ML | SVM · KNN · Bayes Theorm · Regression Models · Decision Trees / Random Forest · Etc |
| Year | Title | Link | Notes / Focus |
|---|---|---|---|
| 2024 | Ensemble Learning Development Based on Transfer Learning for Indonesian Traditional Food Detection | (in migration) | Transfer learning · Ensemble |
| 2023 | Enhancing Small Dataset Performance: Data Augmentation and Transfer Learning in Indonesian Traditional Foods Classification | IEEE Xplore | Data augmentation · Food classification |
| 2023 | A Deep Learning Approach to Outbreak Virus Classification: Utilizing Bidirectional GRU on DNA Sequence of SARS-CoV-2, Zika, Ebola, and MERS | IEEE Xplore | Biosequence DL · BiGRU |
| 2023 | LSTM Variants Comparison for Exchange Rate IDR/USD Forecasting with Rolling Window Cross Validation | IEEE Xplore | Time series · LSTM variants |
| 2022 | The Development of Telegram Bot API to Maximize the Dissemination Process of Islamic Knowledge in 4.0 Era | (in migration) | Conversational automation |
| 2022 | Systematic Literature Review: Virus Prediction Based on DNA Sequences Using ML & DL | IEEE Xplore | Survey · Bioinformatics |
| 2021 | WhatsApp Chatbot Implementation Using Node.js for a Da'wah Media Digitalization | IEEE Xplore | Chatbot · Automation |
- Develop neural network architecture
- Computer vision (detection, etc)
- LLM evaluation & lightweight tuning
- Retrieval + prompt experiments (RAG)
- Ensemble / transfer approaches on datasets
- English & Indonesian-language NLP
“Stay curious.”