首页|Findings from University of Southern California (USC) Update Knowledge of Machin e Learning (Inference Latency Prediction for Cnns On Heterogeneous Mobile Device s and Ml Frameworks)
Findings from University of Southern California (USC) Update Knowledge of Machin e Learning (Inference Latency Prediction for Cnns On Heterogeneous Mobile Device s and Ml Frameworks)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Research findings on Machine Learning are discussed in a new report. According to newsreporting out of Los Angeles, C alifornia, by NewsRx editors, research stated, “Due to the proliferationof infe rence tasks on mobile devices, state-of-the-art neural architectures are typical ly designed usingNeural Architecture Search (NAS) to achieve good tradeoffs bet ween machine learning accuracy andinference latency. While measuring inference latency of a huge set of candidate architectures during NASis not feasible, lat ency prediction for mobile devices is challenging, because of hardware heterogen eity,optimizations applied by machine learning frameworks, and diversity of neu ral architectures.”
Los AngelesCaliforniaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningUni versity of Southern California (USC)
NETL
NSTL
