In what has been described as `a major breakthrough' by computer scientists at Google's mysterious X lab, the company's artificial brain - comprising a neural network of 16,000 computer processors - has learnt to find cat videos!
According to the details shared by the scientists, after exposing the "brain" simulation to 10 million randomly selected YouTube video thumbnails for three days, and later presenting it with a list of 20,000 different items, it was found that the "brain" used a "deep learning" algorithm to identify pictures of cats.
Going by the statistical claims of the scientists, the artificial brain system picked up on the most commonly occurring pictures which featured on YouTube, and was nearly 81.7 percent accurate in detecting human faces. While its accuracy in detecting human body parts was 76.7 percent, its accuracy in identifying cats was 74.8 percent.
Despite the fact that the activity and the eventual findings may sound frivolous to a lot of people, the scientists elaborated that the recognition of cats by the "brain" was a noteworthy achievement because it had not been fed any information on distinguishing characteristics which might help it identify cats.
Highlighting the feat in a paper titled `Building high-level features using large scale unsupervised learning,' the team of scientists at Google's X lab said: "Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not."
- Inquest into Death of Dylan Crean, 3, Finds Communication Failings between Agencies
- Denise Welch Shares Her Experience during Fight against Depression
- Toy Car Helps 16-Year-Old Girl Recover of Paralysis
- Lack of Support Makes Carers in Scotland Fail in Relationships
- Vodafone pays no corporation tax in UK for second consecutive year, despite earning over £5bn