Machine Learning Interpretability Toolkit

From the creator

We will discuss a little about what it means to develop AI in a transparent way. We will introduce our interpretability toolkit which enables you to use different state-of-the-art interpretability methods to explain your models decisions. By using this toolkit during the training phase of the AI development cycle, you can use interpretability output of a model to verify hypotheses and build trust with stakeholders. You can also use the insights for debugging, validating model behavior, and to check for bias. You can also use this toolkit at inferencing time to explain the predictions of a deployed model to the end users. Learn More: Link to the doc: https://docs.microsoft.com/en-us/azure/machine-learning/service/machine-learning-interpretability-explainability?ocid=AID2463683&wt.mc_id=ai-c9-sejuare Link to the sample notebooks: https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/explain-model?ocid=AID2463683&wt.mc_id=ai-c9-sejuare 02:12 – Responsible AI 02:34 – Machine Learning Interpretability 03:12 – Interpretability Use Cases 05:20 - Different Interpretability Techniques 06:45 - Demo Don't miss new episodes, subscribe to the AI Show: https://aka.ms/aishowsubscribe Create a Free account (Azure): https://aka.ms/aishow-seth-azurefree AI Blog: https://aka.ms/openaiblog Fast ML: https://aka.ms/fastml MIT News | AI: https://aka.ms/mitnews Medium | Francesca Lazzeri: https://medium.com/@francescalazzeri Deep Learning vs. Machine Learning: ht

Published 2019-10-15 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.