Driverless AI seeks to build the fastest artificial intelligence (AI) platform on graphical processing units (GPUs). Many other machine learning algorithms can benefit from the efficient, fine-grained parallelism and high throughput of GPUs, which allow you to complete training and inference much faster than with CPUs.
In addition to supporting GPUs, Driverless AI also makes use of machine learning interpretability (MLI). Often times, especially in regulated industries, model transparency and explanation become just as important as predictive performance. Driverless AI utilizes MLI to include easy-to-follow visualizations, interpretations, and explanations of models.
This document describes how to install and use H2O Driverless AI and is based on a pre-release version. For more information about Driverless AI, please see https://www.h2o.ai/driverless-ai/.
- Installing Driverless AI
- Running an Experiment
- Interpreting a Model
- Viewing Explanations
- The Scoring Package
- Viewing Experiments
- Visualizing Datasets
- Appendix A: Driverless AI Transformations
- Appendix B: Using the Driverless AI Python Client