Artificial intelligence (AI) systems that are based on deep learning are changing the electronic devices that surround us and how we interact with them. Phys.org brought this interesting information to our attention in their article, “Make deep learning faster and simpler.”
Every time a computer understands our speech request or an advertisement for something we have been shopping for shows up in our news or social feed, we are living the effects of deep learning.
Sophisticated software systems have been built to perform these types of calculations. They underlie much of the AI we hear about – speech recognition, internet search, image understanding, face recognition, machine learning, and semantic advertising.
Deep learning uses automatic differentiation (AD) in the reverse accumulation mode, for efficiently calculating how adjustments to a large number of controls will affect a result. A series of innovations allows not just reverse-mode AD, but other modes of AD, to be used efficiently.
With deep learning and its massive amounts of computational power, machines can now recognize objects and translate speech in real time.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.