Open Data Science Courses

Modeling Real World Change with Geospatial Data

Curate and validate fresh points-of-interest data for location intelligence, analytics, and business strategy.

• YouTube
• 39 minutes
• Self-Paced
• Free Video

What Kind of AI Can Help Manufacturing Adapt to a Pandemic

Explore how lifelong deep neural networks adapt visual quality inspection to changing manufacturing conditions, learn from limited data, and operate continuously.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

ML Observability - A Critical Piece for Making Models Work in the Real World

Learn how machine learning observability uses performance, drift, data quality, and explainability analysis to diagnose models in production.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

Accelerating the Journey to Document Understanding AI

Learn to leverage existing Document AI tools to turn unstructured documents into structured, decision-ready data without building models from scratch.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Introducing Quine - A Streaming Graph for Modern Data Pipelines

Explore Quine, a streaming graph that uses incremental computation to interpret high-volume data and trigger real-time actions across modern data pipelines.

• YouTube
• 47 minutes
• Self-Paced
• Free Video

The Missing Link- How AI Can Help Create a Safer Society and Better Businesses

A talk on using AI and natural language processing to connect siloed knowledge, improve decisions, and keep humans in the loop across businesses and public services.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Dataset Management for Computer Vision - Important Component to Delivering Computer Vision Solutions

Learn how dataset management helps computer vision teams align business goals, control corner cases, and adapt models to evolving real-world data.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

The Role of Data Virtualization in AI-ML Projects - A Demonstration

Demonstrates how data virtualization unifies live data sources, streamlines cleansing and transformation, and feeds an AI/ML project without physically copying data.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Building Real-Time ML Pipelines the Easy Way

Build operational machine learning pipelines that process streaming data in real time, reuse batch and serving logic, and deploy monitored models for fraud and churn prediction.

• YouTube
• 43 minutes
• Self-Paced
• Free Video

Medical Imaging with Azure Machine Learning

Explore Azure Machine Learning workflows for medical imaging, from labeling and brain-tumor experiments to federated learning and automated cell segmentation.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Overcoming Imposter Syndrome in STEM

A panel-led webinar explains imposter syndrome in STEM and offers practical ways to manage self-doubt through facts, validation, contribution, feedback, and peer support.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

Relationships Matter - Using Connected Data for Better Machine Learning

See how graph-native machine learning turns relationships into predictive features through embeddings, link prediction, node classification, and hands-on Neo4j demonstrations.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Evolution of Efficient and Robust AutoML Systems

Explore how multi-fidelity optimization, portfolio construction, and automated policy selection make AutoML systems more efficient and robust.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Git-Based CI-CD for ML

Learn how Git-based ML pipelines automate model training, review, versioning, deployment, and monitoring for production machine learning.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

Interpretable Machine Learning to Model Drug Perturbations in Single Cell Genomics

An interpretable compositional autoencoder models drug and genetic perturbations in single-cell transcriptomes to predict dosage-specific effects and combinatorial interactions.

• YouTube
• 36 minutes
• Self-Paced
• Free Video