Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS

machine learning data

Do Wide and Deep Networks Learn the Same Things?

 Originally published in Google AI Blog, May 4, 2021. A common practice to improve a neural network’s performance and tailor it to available computational resources is to adjust the architecture depth and width. Indeed, popular families of neural networks,  including  EfficientNet, ResNet and Transformers, consist of a set of architectures of flexible depths and widths. However, beyond the effect

Sharing Learnings About Our Image Cropping Algorithm

 In October 2020, we heard feedback from people on Twitter that our image cropping algorithm didn’t serve all people equitably. As part of our commitment to address this issue, we also shared that we’d analyze our model again for bias. Over the last...

The Four Most Common Fallacies About AI

 Originally published in VentureBeat, May 8, 2021. The history of artificial intelligence has been marked by repeated cycles of extreme optimism and promise followed by disillusionment and disappointment. Today’s AI systems can perform complicated tasks in a wide range of areas, such...

How Image Search Works at Dropbox

 Originally posted in Dropbox.tech, May 11, 2021 Photos are among the most common types of files in Dropbox, but searching for them by filename is even less productive than it is for text-based files.  When you’re looking...