Notebooks, code samples, sample apps, and other resources that demonstrate how to use, develop and manage machine learning and generative AI workflows using Google Cloud Vertex AI.

The neuromuscular model notebook is an interactive tool for studying the underlying mechanisms of electromyogram (EMG) and force generation. The model, which was based on previous studies (see references below), can be used for research purposes as well as a teaching platform.

Notebooks for Yunjun et al. (2021) on Kirishima volcanic complex in Japan

Credit Card Fraud Detection Model with an accuracy of 91.24%.Uses AWS for training and tuning.

Translating language to Greek using Trained Model given in python notebook

Training Notebooks for Traffic Models

A well-organized collection of Jupyter notebooks covering the full machine learning journey—from data preprocessing and classic algorithms to deep learning, NLP, and reinforcement learning. Ideal for learners and professionals to explore, experiment, and master ML with real code.

Jupyter notebooks implementing AI, Machine Learning and Deep Learning algorithms in pure TensorFlow

Kaggle Notebooks used at competitions or tutorials

Machine Learning Concepts And Models using Octave and Jupyter Notebook

a model that predicts some binary target (class) based on two features

A modern, intelligent web application that uses Random Forest machine learning to detect and classify malicious URLs in real-time. Built with Streamlit, featuring an advanced whitelist override system and beautiful interactive visualizations.

This notebook performs a classification task on the MAGIC Gamma Telescope dataset.

These notebooks contain advanced analysis of ML models of different kind of datasets

Built from a JupyterLab notebook → refactored into a reusable API → deployed with an interactive dashboard.

code and notebooks related to the training, evaluation, and application of the FINSURF-adjusted prediction model.

A notebook that basically generates random linear and parabolic data and then it fits various curves (polynomials with different degrees) in that data.

Day 6 of Phase 2: AI System Building from the Databricks 14 Days AI Challenge – 2 (Advanced). Trained Logistic Regression and Random Forest Models, Performed Manual Hyperparameter tuning due to Workspace Constraints, Evaluated using ROC-AUC, & Analyzed Near-Perfect Results with Leakage Awareness.

Can be used as-is for better slashed zeros recognition (especially with the Consolas font). This Repository includes a Jupyter notebook with instructions to train/finetune a Tesseract OCR model.

An interactive marimo python notebook that turns the central claim of "Why do LLMs attend to the first token?" (Barbero et al., 2025) into something you can see, poke, and break.