Presentation: Interpretable Machine Learning Products
Share this on:
Abstract
Interpretable models are easier to improve. Regulators and society can better trust them to be safe and nondiscriminatory. They can also offer insights that can be used to change real-world outcomes for the better. But because there is a central tension between accuracy and interpretability interpretability can be hard to ensure.
I'll explore both the product case for interpretability and the academic research that is starting to make the inner workings of black box models such as deep neural networks easier to understand. In particular, I'll look at the application of a new open source tool called LIME to customer churn, image classification and black box NLP models.
Tracks
-
Groking Timeseries & Sequential Data
Techniques, practices, and approaches, including image recognition, NLP, predictions, & modeling.
-
Deep Learning in Practice
Deep learning lessons using Tensorflow, Keras, PyTorch, Caffe including use cases on machine translation, computer vision, & image recogition.
-
AI Meets the Physical World
Where AI touches the physical world, think drones, ROS, NVidia, TPU and more.
-
Papers to Production: CS in the Real World
Groundbreaking papers make real world impact.
-
Solving Software Engineering Problems with Machine Learning
Anomaly detection, ML in IDE's, bayesian optimization for config. Machine Learning techniques for more effective software engineering.
-
Predictive Architectures in the Real World
Case Study focused look at end to end predictive pipelines from places like Salesforce, Uber, Linkedin, & Netflix.