AI Engineer · Data Scientist

Applied AI
Research Archive

Machine learning & deep learning research, from classical algorithms to large language models.

Explore research Github
20
Research Projects
4+
Years Python
2+
Years AI/ML
100%
Open Source

How I approach machine learning

A current view of my research workflow across 20 full projects: from data analysis and model building to deployment, databases, and MLOps.

I approach machine learning as a full research-to-production pipeline. I start with Exploratory Data Analysis (EDA), data cleaning, preprocessing, feature engineering, and visualization to understand the real structure of the data before choosing a model.

From there, I build a strong baseline first, then improve it through cross-validation, metric tracking, error analysis, threshold calibration, and controlled experiments. I care about what each model learns, where it fails, and whether the final result is actually useful beyond a notebook score.

My current project archive now covers medical AI, computer vision, NLP, tabular machine learning, regression, classification, object detection, segmentation, web scraping, and data engineering. The newer projects go beyond notebooks into deployed systems with APIs, databases, Docker, model logging, and experiment tracking.

For deep learning projects, I focus on practical architecture decisions: CNN backbones for image classification, YOLO-style detection for localization, U-Net-style segmentation for medical masks, and sequence models such as BiLSTM, attention, Siamese networks, embeddings, TF-IDF, and NLP preprocessing for text tasks.

For classical machine learning, I still treat algorithms as serious production tools. I compare linear models, SVMs, tree models, Random Forests, XGBoost, LightGBM, CatBoost, voting ensembles, feature engineering strategies, and tabular validation workflows before deciding whether deep learning is really necessary.

The direction is moving from isolated experiments toward complete AI systems: Lung Disease Detection, Quora Question Pairs, Disaster Tweets, SMS Spam, Global Wheat Detection, Cassava Leaf Diseases, TMDB Revenue, and earlier classical ML/data-analysis projects all connect model performance with real implementation practice.

On the deployment side, I connect trained models with real interfaces using FastAPI, Docker, SQL databases, object storage, ONNX export, inference pipelines, prediction logging, and MLOps tools such as MLflow, Airflow, Kafka, and Optuna. The goal is not only to train models, but to understand how they become reliable AI products.

Core Workflow

EDA Data Cleaning Data Preprocessing Feature Engineering Visualization Cross-Validation K-Fold Error Analysis Threshold Calibration F1 Optimization Confusion Matrix MSE MAE

Deep Learning & NLP

TensorFlow/Keras PyTorch Neural Networks CNN BiLSTM LSTM Attention Siamese Network Multi-Head Attention Bahdanau Attention GloVe Embeddings TF-IDF N-grams Tokenization Text Vectorization NLTK VADER WordCloud

Computer Vision

OpenCV Image Classification Object Detection Semantic Segmentation YOLOv8 U-Net EfficientNet DenseNet InceptionV3 MobileNetV3 Bounding Boxes COCO mAP Dice Score TTA Weighted Boxes Fusion

Classical ML & Ensembles

Scikit-Learn XGBoost LightGBM CatBoost Gradient Boosting Random Forest Decision Tree SVC / SVM Logistic Regression Logistic Regression CV KNN GaussianNB SVR XGBRF Majority Voting Ensemble Voting

Deployment & MLOps

FastAPI Docker Docker Compose ONNX ONNX Runtime MLflow Airflow Kafka Optuna Uvicorn Pydantic Jinja2 Model Deployment Database Logging Object Storage Model Architecture Export

Data, Web & Storage

Python Pandas NumPy Matplotlib Seaborn HTML CSS JavaScript PostgreSQL Microsoft SQL Server SQLite SQLAlchemy Redis MongoDB Supabase Storage BeautifulSoup Requests Regex JSON lxml feedparser newspaper3k PyMongo SciPy joblib pickle TQDM IPython TorchMetrics KerasCV ensemble-boxes

Featured projects

A visual project vitrine where image scale represents project priority.

View all projects →

Areas of expertise

Deep technical skills developed through research and competition.

Connect with me

Amir Mohammad Askari — AI engineer and researcher.