Advancing state-of-the-art image recognition with deep learning on hashtags

Advancing state-of-the-art image recognition with deep learning on hashtags

  • May 4, 2018
Table of Contents

Advancing state-of-the-art image recognition with deep learning on hashtags

Image recognition is one of the pillars of AI research and an area of focus for Facebook. Our researchers and engineers aim to push the boundaries of computer vision and then apply that work to benefit people in the real world — for example, using AI to generate audio captions of photos for visually impaired users. In order to improve these computer vision systems and train them to consistently recognize and classify a wide range of objects, we need data sets with billions of images instead of just millions, as is common today.

Source: facebook.com

Tags :
Share :
comments powered by Disqus

Related Posts

We Need Bug Bounties for Bad Algorithms

We Need Bug Bounties for Bad Algorithms

Algorithmic auditors are a growing discipline of researchers specializing in computer science and human-computer interaction. They employ a variety of methods to tinker with and uncover how algorithms work, and their research has already sparked public discussions and regulatory investigations into the most dominant and powerful algorithms of the Information Age. From Uber and Booking.com to Google and Facebook, to name a few, these friendly auditors already uncovered bias and deception in the algorithms that control our lives.

Read More
Measuring the Intrinsic Dimension of Objective Landscapes

Measuring the Intrinsic Dimension of Objective Landscapes

In our paper, Measuring the Intrinsic Dimension of Objective Landscapes, to be presented at ICLR 2018, we contribute to this ongoing effort by developing a simple way of measuring a fundamental network property known as intrinsic dimension. In the paper, we develop intrinsic dimension as a quantification of the complexity of a model in a manner decoupled from its raw parameter count, and we provide a simple way of measuring this dimension using random projections. We find that many problems have smaller intrinsic dimension than one might suspect.

Read More
DeepMind papers at ICLR 2018

DeepMind papers at ICLR 2018

Between 30 April and 03 May, hundreds of researchers will gather in Vancouver, Canada, for the Sixth International Conference on Learning Representations. Here you will find details of all DeepMind’s accepted papers.

Read More