I build intelligent, interpretable, and efficient AI systems that combine deep learning, computer vision, time-series forecasting, and signal processing — transforming data into insight and impact.
- 🔬 Researching AI for Healthcare, Explainable Multimodal AI, and Time-Series Forecasting
- ⚙️ Experienced in Deep Learning, Transformer Architectures, and Reinforcement Learning.
- 💡 Passionate about bridging research and practical applications in Computer Vision.
- 🌍 Based in Taiwan | 🌱 Constantly exploring PyTorch, Vision Transformers, and MLOps
- 📫 Reach me via: rasoulameri.github.io/
| Name | Description | Repository |
|---|---|---|
| ML_1 | AI Programming and XAI Using Python. This repository covers environment setup, Python fundamentals, data cleaning, model training, and explainable AI using SHAP for KNN and other models. | Repo Link |
| Name | Description | Repository |
|---|---|---|
| DL_1 | A complete, straightforward digit classification project built with PyTorch, featuring CNN-based training, evaluation metrics, confusion matrix visualization, and XAI using Grad-CAM. | Repo Link |
| Name | Description | Repository |
|---|---|---|
| CV_1 | Implements a UNet-based medical image segmentation framework for precise detection of the carina and endotracheal tube tip, supporting automated clinical evaluation of airway placement. | Repo Link |
| CV_2 | A hybrid CNN–Transformer framework for precise industrial surface defect detection and segmentation, integrating Vision Transformer (ViT) with convolutional modules to effectively capture both local texture details and global contextual features. | Repo Link |
| Name | Description | Repository |
|---|---|---|
| TSF_1 | A hybrid machine learning framework for river discharge forecasting that combines ensemble regression models with the Arithmetic Optimization Algorithm (AOA) for hyperparameter tuning and next-day flow prediction. | Repo Link |
