ENERGY | WIRELESS | NANOTECH | MEMS | OPTICS | QUANTUM | 3D | CHIPS | ALGORITHMS

Tuesday, October 16, 2012

#ALGORITHMS: "Hyper-threading: Perfect for Neural Networks"

Today artificial neural networks (ANNs) are experiencing a resurgence, as a result of the success of high-profile applications that instill smarts into all sorts of apps, such as those using voice dictation, gesture navigation and knowledge representation. Luckily, the emerging legions of multi-core processors from Intel, AMD, Freescale and others support multiple threads, which is ideal for programming neural networks: R. Colin Johnson

Biological neurons (upper left) are emulated by artificial neural network (ANN) mapping concepts that sum inputs (upper right) then supply an output (bottom) filtered by an activation function. Source: Intel

Here is what Go-Parallel.com says about ANNs: Artificial neural networks (ANNs) are used today to learn solutions to parallel processing problems that have proved impossible to solve using conventional algorithms. From cloud-based, voice-driven apps like Apple’s Siri to realtime knowledge mining apps like IBM’s Watson to gaming apps like Electronic Arts’ SimCity, ANNs are powering voice-recognition, pattern-classification and function-optimization algorithms perfect for acceleration with Intel hyper-threading technology.
Further Reading