New technique vastly improves image recognition in AI

New technique vastly improves image recognition in AI

ga('send', 'event', 'Computing', 'article', 'article-industry-impression', {nonInteraction: true});

Computer scientist Geoffrey Hinton was instrumental in developing image-recognition software used today for everything from transcribing speech to fighting online trolls. In two recent research papers, Hinton has developed a new approach to image recognition software that could help AI systems act more like humans. Hinton’s system aims to remedy a weakness of exiting machine-learning systems, which is that these systems need a large number of example photos in order to reliably recognize even simple objects. This is because the software is limited in its ability to generalise what it learns from one image to another, such as understanding that an object is the same when seen from a new viewpoint. For example, teaching a computer to recognize a dog from any angle requires inputting photos of the dog from thousands of different angles.

Spotted another good idea???
Join our network and earn rewards

Add to my folders:

Select any pre-existing folders to add the current post to. Posts will be added to a 'default' folder if nothing is selected.

Create a new folder (Optional)

Separate with commas to add multiple folders. The current post is automatically added to any new folders you create (e.g. my new folder, my second folder).

Add

Remove from my folders

Below is a list of folders where the current post appears in. Select the folder you wish to remove it from.

Update