AI Safety Needs Social Scientists
The goal of long-term artificial intelligence (AI) safety is to ensure that advanced AI systems are reliably aligned with human values — that they reliably do things that people want them to…
Learn more Industry news
How to Make a Series of Matching Dashboards in Excel
Do you need a series of matching dashboards? One per program, school, or state? Copying and pasting is tedious and destined for typos. Instead, produce a series of matching dashboards…
Learn more
Activation Atlas
Introduction Neural networks can learn to classify images more accurately than any system humans directly design. This raises a natural question: What have these networks learned that allows them to…
Learn more
Visualizing memorization in RNNs
Memorization in Recurrent Neural Networks (RNNs) continues to pose a challenge in many applications. We’d like RNNs to be able to store information over many timesteps and retrieve it when…
Learn more
A Visual Exploration of Gaussian Processes
Even if you have spent some time reading about machine learning, chances are that you have never heard of Gaussian processes. And if you have, rehearsing the basics is always…
Learn more
Open Questions about Generative Adversarial Networks
By some metrics, research on Generative Adversarial Networks (GANs) has progressed substantially in the past 2 years. Practical improvements to image synthesis models are being made almost too quickly to…
Learn more
How to Make Your First Tableau Dashboard
Want to get started with Tableau? Here’s a step-by-step guide to making your very first Tableau dashboard. In less than an hour, you’ll be able to install the free version…
Learn more
College Football Through Data Visualization
Heated rivalries, conference realignment, stadium capacity, fan maps, game predictions and more. Explore the data visualizations on all things college football. Lead Solution Engineer, Tableau Source link
Learn more
A Discussion of ‘Adversarial Examples Are Not Bugs, They Are Features’
On May 6th, Andrew Ilyas and colleagues published a paper outlining two sets of experiments. Firstly, they showed that models trained on adversarial examples can transfer to real data, and…
Learn more
A Discussion of ‘Adversarial Examples Are Not Bugs, They Are Features’: Discussion and Author Responses
We want to thank all the commenters for the discussion and for spending time designing experiments analyzing, replicating, and expanding upon our results. These comments helped us further refine our…
Learn more