
The researchers’ neural network was fed video from 26 terabytes of video data downloaded from the photo-sharing site Flickr. Researchers found the network can interpret natural sounds in terms of image categories. For instance, the network might determine that the sound of birdsong tends to be associated with forest scenes and pictures of trees, birds, birdhouses, and bird feeders. Image: Jose-Luis Olivares/MIT
From Larry Hardesty at the news office of the Massachusetts Institute of Technology an interesting article on machine-learning, which we thought was going to be about a new app for birders but it is a much broader finding:
Computer learns to recognize sounds by watching video
Machine-learning system doesn’t require costly hand-annotated data.
Watch Video
In recent years, computers have gotten remarkably good at recognizing speech and images: Think of the dictation software on most cellphones, or the algorithms that automatically identify people in photos posted to Facebook. Continue reading


