In Haskell, the type signature written above a function is a compact specification: what goes in, what comes out, which effects (I/O, state, parsing) are involved, and which constraints apply to polymorphic arguments.

Experimental Python project for automated molecular generation, evaluation, and statistical learning.

Dissolved-oxygen forecasting, sensor-fault detection and alert triage on public USGS stream data. Calibrated 1–24 h forecasts, honest baselines and confidence intervals, FastAPI service, interactive dashboard.

AI-based cloud microservices monitoring, failure prediction, root cause analysis, incident detection, and recovery recommendation system using LSTM, FastAPI, React, Docker, Kubernetes, Prometheus, Grafana, and Jaeger.

AI Knowledge Assistant using Retrieval-Augmented Generation (RAG), local embeddings, vector search, and Ollama.

IBM AutoAI project for predicting employee salaries using machine learning

Reproducible n-gram screening of language-model training data for overlap with evaluation benchmarks.

Automatic detection and mitigation of IoT attacks with machine learning over SDN (Mininet + Ryu) · Detección y mitigación automática de ataques IoT con ML sobre SDN — UCC undergraduate thesis

Hybrid Quantum-Classical ML platform for early disease detection using biomedical data. Integrates Quantum Variational Classifier (QVC) and SVM with Quantum Kernel for disease classification, benchmarking, and exploring quantum-enhanced healthcare AI. Built with Python, Qiskit/PennyLane & Scikit-learn.

A public home for AI Research Moroccan Network (AIRMN), a global Moroccan AI research community.

Text emotion classification using TF-IDF, machine learning, and a Streamlit interface. Compares Naive Bayes, Logistic Regression, and Linear SVM with hyperparameter tuning.

GPU-accelerated data analysis with NVIDIA RAPIDS (cuDF, cuML) on 3M NYC taxi trips: 21.5x faster than pandas/scikit-learn on a Tesla T4.

An open roadmap from Python fundamentals to data science and AI.

AI-powered cardiac risk prediction using machine learning to estimate CAD, LAD, LCX, and RCA risk, featuring an interactive 3D heart visualization and a Streamlit web app. For educational and research purposes only.

DGA domain detection: linguistic features + n-gram language model + gradient boosting (AUC 0.99, 0.27% FPR), per-family and unseen-family evaluation, and DNS-log hunting of infected hosts and C2 candidates.

A multi-agent AI system that autonomously explores data, engineers features, trains and evaluates ML models, and self-corrects via an LLM reviewer — all running in a sandboxed Docker environment with a FastAPI + Streamlit interface.

AI-powered predictive maintenance system using Python, Machine Learning, and simulated IoT sensor data to predict equipment failure and visualize risk through an interactive dashboard.

Biscuit defect classification using Classical Machine Learning, TinyVGG CNN, and EfficientNet-B0 Transfer Learning.

Machine learning project for customer churn prediction using Logistic Regression, Decision Tree, Random Forest and Gradient Boosting with model evaluation and visualization.

A self-learning Python predictor that analyzes human number-selection patterns using adaptive statistical models, persistent profiles, and real-time accuracy tracking.

Ink into Stars: 108 Lectures on Machine Learning | 《墨点成星：机器学习一百零八讲》中英双语讲义与配套代码

Employee attrition segmentation on IBM HR data with K-Means, GMM, Agglomerative & K-Prototypes + PCA | Çalışan devir hızı kümeleme analizi

Health Insurance Claim Fraud Risk Scoring System: Pendekatan statistik dan pembelajaran mesin (LightGBM & CatBoost) untuk mengesan, mengkuantiti, dan mengutamakan risiko penipuan tuntutan insurans kesihatan di bawah kapasiti audit yang terhad (5%) menggunakan metrik utama NormalizedRecall@5%.