What we need is interpretable and not explainable machine learning

- About this Session
- Session Resources
All models are wrong and when they are wrong they create financial or non-financial harm. Understanding, testing and managing potential model failures and their unintended consequences are the key focus of model risk management, particularly for mission critical or regulated applications. This is a challenging task for complex machine learning models and having an explainable model is a key enabler. Machine learning explainability has become an active area of academic research and an industry in its own right. Despite all the progress that has been made, machine learning explainers are still fraught with weakness and complexity. In this talk, I will argue that what we need is an interpretable machine learning model, one that is self-explanatory and inherently interpretable. I will discuss how to make sophisticated machine learning models such as Neural networks (Deep Learning) as self-explanatory models.
Featured Presenters
Supported By

ATARC
The Advanced Technology Academic Research Center (ATARC) is a 501(c)(3) non-profit organization that provides a collaborative forum for government, academia and industry to resolve emerging

Blue Prism
As the leading provider of Intelligent Automation, Blue Prism Government Solutions (BPGS) helps the intelligence community accelerate their data centric mission

Carahsoft
Carahsoft is a trusted Government IT Solutions Provider working with reseller partners, system integrators, and manufacturers to proving leading IT solutions to government markets.

ClearML
Allegro AI makes ML and DL researchers more effective by giving them tools to manage their own experiments and data. The company’s open source ClearML

Comet
Comet provides a self-hosted and cloud-based MLOps solution that enables data scientists and teams to track, compare, explain and optimize experiments and models.

DataRobot
DataRobot is the leader in enterprise AI, delivering trusted AI technology and ROI enablement services to global enterprises. DataRobot’s enterprise AI platform democratizes data science with end-to-end automation for building, deploying, and managing machine learning models.

Datatron
Production AI Model Management at Scale
Automate the standardized deployment, monitoring, governance, and validation of all your models to be developed in any environment. A single, production-grade environment for all your SAS, R, Machine Learning, and Regression model needs

Modzy
Modzy is the secure ModelOps platform that enables AI at enterprise scale. Modzy solves last mile challenges with deploying, managing, monitoring and securing AI models in production systems, allowing teams to start seeing the real value of AI.

Pactera Edge
Pactera EDGE is a global digital and technology services company. We design, build and optimize human-centric intelligent digital platforms.

Veritone
Transform audio, video, and other data sources into actionable intelligence with Veritone’s aiWARE.

Zorroa
Zorroa’s no-code ML integration platform makes process automations with machine learning APIs from GCP, AWS, and Azure accessible in under an hour. Its platform enables media technologists to stand up rapid-cycle experiments and scale their ML projects without code, data prep, or vendor lock-in.