Deep neural networks are a type of artificial intelligence, capable of recognizing and classifying data. It is what makes a self-driving car tell a person apart from a traffic cone, and what makes Spotify effectively the songs for your “Discover Weekly” playlist. These deep neural networks, however, need a lot of computing power, as well as memory, and this is too much for an average smartphone to handle.
Typically, a mobile device needs to be connected to the internet to have access to a deep neural network. The phone collects data, but the processing is done on remote servers—this is why you can't talk to Siri when your iPhone is in airplane mode.
Enter researchers from Northeastern University, who were able to to find a way to run deep neural networks on a smartphone or similar system.
Using their method, the networks can execute tasks up to 56 times faster than demonstrated in previous work, without losing accuracy.
More details about this over at TechXplore.
(Image Credit: GDJ/ Pixabay)