Artificial intelligence (AI) systems that are based on deep learning are creating much change and energy in and around the electronic devices that are a part of our daily lives. This interesting topic came to us from ECN Magazine in their article, “Make Deep Learning Faster and Simpler.”
Deep learning requires power and enormous clusters of computers. Remember that each time a computer understands our speech. However, teams are working on methods that will allow more modest computers to achieve similar results in less time.
Deep learning uses a particular kind of calculus at its heart: a clever technique, called automatic differentiation (AD) in the reverse accumulation mode, for efficiently calculating how adjustments to a large number of controls will affect a result. One major limitation on these deep learning systems is that they support this particular AD calculation very rigidly.
Because the AD operation requires a great deal of computer memory, it limits the size and sophistication of the deep learning systems that can be built.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.
