Dive Brief:
- On Thursday, Microsoft introduced a deep learning acceleration platform designed for real-time AI, according to a company blog post.
- Project Brainwave uses DNN synthesized on field programmable gate array (FPGA) chips from Intel; it is also compatible with a variety of software, including Microsoft's Cognitive Toolkit and Google's TensorFlow.
- The move to real-time AI is important because cloud infrastructure processes live data streams such as user interactions, search queries, videos and sensor streams, said a Microsoft engineer in the post.
Dive Insight:
As AI rapidly advances, tech companies are in a race to solve critical hangups.
Earlier this month, IBM announced PowerAI DDL, a new technique designed to reduce the time it takes to train distributed deep learning systems. Now Microsoft is similarly increasing efforts to up AI speed.
Quickly processing AI requests has long been a goal, but until now there were too many required steps to make it a reality. Microsoft removed software from the process, allowing hardware to handle the requests faster using Intel’s new chip, which is capable of 39.5 teraflops of machine learning tasks with less than a millisecond of latency.
This new platform is an important step to achieving AI capable of mirroring the way humans think and enabling AI and machine-based systems to complete previously impossible tasks.
