The Evaluator
Your go-to blog for insights on AI observability and evaluation.
Showing 431–440 of 458 posts (page 44 of 46)
Coded Bias: An Insightful Look At AI, Algorithms And Their Risks To Society
Coded Bias is Netflix’s deepest dive yet into the state of artificial intelligence, and the issues it confronts are uncomfortably relevant. As the film highlights, algorithms and AI models are designed to mirror and predict real life as closely as possible; however, commercially available facial recognition programs have a severe algorithmic bias against women and people…
Google Maps and Climate Change: Using AI to Help a Changing Planet
In 2020, the environment experienced a silver lining of sorts. With social distancing keeping people off the roads and out of the skies, global greenhouse gas emissions plunged by roughly 2.4 billion tons in 2020, a 7% drop from 2019. As the masses slowly return to the roads and air, some that hoped a ‘green…
Why Business Executives Should Be Hip To ML Tools
I have spent most of my professional life in the age of AI and ML. During earlier times at Uber, I worked with models that estimated ETAs, calculated dynamic pricing and even matched riders with drivers. My co-founder Jason previously led video ad company TubeMogul (acquired by Adobe), which relied on ML to ensure that its…
Sign up for our newsletter, The Evaluator — and stay in the know with updates and new resources:
The Only 3 ML Tools You Need
Image by Author At a rapid pace, many machine learning techniques have moved from proof of concepts to powering crucial pieces of technology that people rely on daily. In attempts to capture this newly unlocked value, many teams have found themselves caught up in the fervor of productionizing machine learning in their product without the right…
Welcome to Arize AI, Tammy!
We’re excited to introduce Tammy Le, our newest Arizer! Tammy joins Arize AI as the Vice President of Marketing and Strategy. Tammy was most recently the Head of Ecosystem and Cloud Migrations Marketing at Atlassian and before that, Tammy was the Head of Product Marketing at Adobe. Tammy holds a bachelor’s degree in Psychology from…
The Chronicles of AI Ethics: The Man, The Machine, And The Black Box
Today, machine learning and artificial intelligence systems, trained by data, have become so effective that many of the largest and most well-respected companies in the world use them almost exclusively to make mission-critical business decisions. The outcome of a loan, insurance or job application, or the detection of fraudulent activity is now determined using processes…
The Playbook to Monitor Your Model’s Performance in Production
As Machine Learning infrastructure has matured, the need for model monitoring has surged. Unfortunately this growing demand has not led to a foolproof playbook that explains to teams how to measure their model’s performance. Performance analysis of production models can be complex, and every situation comes with its own set of challenges. Unfortunately, not every…
Welcome to Arize, Kunal!
We’re excited to introduce Kunal Shah, our newest Arizer! Kunal will be joining our amazing Front-end Engineering team. Kunal was most recently at Omada Health and Pandora where he was a front-end engineer. Kunal holds a bachelor’s degree in Computer Science from the University of Southern California. Kunal had trouble recalling a time when he…
The Model’s Shipped; What Could Possibly go Wrong?
In our last post we took a broad look at model observability and the role it serves in the machine learning workflow. In particular, we discussed the promise of model observability & model monitoring tools in detecting, diagnosing, and explaining regressions models that have been deployed to production. This leads us to a natural question…
Arize AI Partners with Spell to Bring ML Observability to the Spell Platform
This week we’re announcing our new partnership with Spell! There is a vast difference between the offline environments where models are trained and production environments where they are served. This training/serving skew often leads to data science teams trying to troubleshoot their models performance once they are deployed. However, most machine learning teams have little to…
