Join us for Code @ Think 2019 | San Francisco | February 12 – 15 Register now Limited availability
Artificial IntelligenceData ScienceMachine Learning
By Alex Jones December 20, 2018,December 20, 2018
The new Monitor WML models with AI OpenScale code pattern shows you how to gain insight into a machine learning model using IBM AI OpenScale. The pattern provides examples of how to configure the AI OpenScale service. You can then enable and explore a model deployed with Watson Machine Learning, and create fairness and accuracy measures for the model.
IBM AI OpenScale is an open platform that enables organizations to automate and operate their AI across its full lifecycle. AI OpenScale provides a powerful environment for managing AI and ML models on IBM Cloud, IBM Cloud Private, or other platforms. It offers the following benefits:
Open by design: AI OpenScale provides insights into the health of ML and DL models – performance, as well as accuracy and fairness of outcomes – built using any frameworks or IDEs, and deployed on any model-hosting engine.
Fairer outcomes: AI OpenScale detects and helps mitigate model biases to highlight possible fairness issues. The platform provides plain text explanations of the data ranges that have been impacted by bias in the model, and visualizations to help data scientists and business users understand the impact on business outcomes. As biases are detected, AI OpenScale automatically creates a de-biased companion model that runs beside the deployed model, thereby previewing the expected fairer outcomes to users without replacing the original model.
Explanation of transactions: AI OpenScale helps enterprises bring transparency and auditability to AI-infused applications by generating explanations for individual transactions, including the attributes that were used to make the prediction and weightage of each attribute.
Automated AI creation: Neural Network Synthesis (NeuNetS), available in this update as a beta, automatically synthesizes neural networks by fundamentally architecting a custom design for a given data set. In the beta, NeuNetS will support image and text classification models. NeuNetS reduces the time and lowers the skill barrier required to design and train custom neural networks. This makes those networks more accessible to non-technical subject matter experts and helps data scientists be more productive.
Monitor WML models with AI OpenScale builds on the Prediction using Watson Machine Learning pattern. It uses the model created in that previous pattern as an example for management using AI OpenScale.
We hope you’ll use this pattern to ramp up your AI and machine learning skills. Please try it out and let us know what you think.
For more information on AI OpenScale, see the following pages:
Get the Code »
Artificial IntelligenceJupyter notebook+
Back to top