Machine Learning – Microsoft’s object classification system (Project Adam)

So Microsoft have claimed to have produced an object classification system that has double the accuracy with 30 times fewer machines (although it may have taken longer to train) than other state-of-the-art systems. I presume they are basing this off Google and Stanford’s attempt which was published here  http://arxiv.org/pdf/1112.6209.pdf. Google’s implementation achieved “15.8% accuracy in recognizing 22,000 object categories from ImageNet”. Which means Microsoft’s attempt should achieve at-least 31.6% as they have used the same dataset. We’l have to wait for the publication of their paper which is in review to see the real results and find out if it is more than just hyperbole.

 

Full article here:

http://research.microsoft.com/en-us/news/features/dnnvision-071414.aspx

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s