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.
Proposed Tracks
-
Real-World Data Engineering
Showcasing DataEng tech and highlighting the strengths of each in real-world applications.
-
Deep Learning Applications & Practices
Deep learning lessons using Tensorflow, Keras, PyTorch, Caffe across machine translation, computer vision.
-
AI Meets the Physical World
The track where AI touches the physical world, think drones, ROS, NVidea, TPU and more.
-
Data Architectures You've Always Wondered About
How did they do that? Real-time predictive pipelines at places like Uber, Self-Driving Cars at Google, Robotic Warehouses from Ocado in the UK, are all possible examples.
-
Applied ML for Software
Practical machine learning inside the data centers and on software engineering teams.
-
Time Series Patterns & Practices
Stocks, ad tech/real-time bidding, and anomaly detection. Patterns and practices for more effective Time Series work.