Analysis of Microsoft's 2026 Global ML Building Footprints dataset, including technical setup and data exploration using DuckDB and QGIS.
A technical exploration of the ICMM's global mining dataset, detailing the setup, tools, and process for data analysis using Python, DuckDB, and QGIS.
Analysis of Foursquare's newly open-sourced Points of Interest (POI) dataset, covering its significance, data preparation, and visualization.
Exploration of Microsoft's 1.4 billion global building footprint dataset, created via ML on satellite imagery, including setup and analysis steps.
Analyzing the Global Streetscapes dataset, a massive collection of AI-labeled street view imagery, using Python, DuckDB, and a high-performance workstation.
Strategies for improving LLM performance through dataset-centric fine-tuning, focusing on instruction datasets rather than model architecture changes.
Explores dataset-centric strategies for fine-tuning LLMs, focusing on instruction datasets to improve model performance without altering architecture.
A hands-on exploration of PyTorch's new DataPipes for efficient data loading, comparing them to traditional Datasets and DataLoaders.
A hands-on exploration of PyTorch's new DataPipes for efficient data loading, comparing them to traditional Datasets and DataLoaders.
Explores the application of classic software design patterns, like the Factory pattern, to machine learning code and systems, using examples from PyTorch, Gensim, and Hugging Face.
Explains a JSON payload issue when pushing data to a Power BI Hybrid dataset and provides a workaround using the correct REST API structure.
A tutorial on text data classification using the BBC news dataset and PHP-ML for machine learning, covering data loading and preprocessing.
Overview of new features, changes, and fixes in PHP-ML 0.7.0, a machine learning library for PHP developers.
