On-demand Internet streaming service Netflix is reportedly developing ‘Deep Learning’ technology that could better forecast what users want to watch.
Making use of neural networks, the new system will be able to detect viewers’ faces in photos, study their tastes and habits, as well understand their interests to a certain extent.
Netflix would use its dashboard to develop viewing suggestions on more or less human level, as per the data feed to it.
Netflix said in a statement that many researchers have pointed out that most of the algorithmic techniques used in the trendy Deep Learning approaches have been known and available for some time.
"Much of the more recent innovation in this area has been around making these techniques feasible for real-world applications," the company added.
Netflix follows the path of web majors Google and Facebook in enhancing functionalities ranging from voice recognition to image tagging, while it plans to run the Deep Learning algorithms on Amazon Web Services, rather than via its own hardware.
"We wanted to use a reasonable number of machines to implement a powerful machine learning solution using a Neural Network approach," the company added.
"We also wanted to avoid needing special machines in a dedicated data centre and instead leverage the full, on-demand computing power we can obtain from AWS.
