摘要
由一名新闻记者-机器人与机器学习日报的工作人员新闻编辑每日新闻-调查人员讨论机器学习的新发现。根据消息来源来自密苏里州圣路易斯的新sRx通讯员，研究称，“线性实值计算”过度分布的数据集在许多应用程序中很常见，最明显的是作为机器学习的一部分推论。具体地说，量化的线性计算，即，当系数受到限制时对于一组预先确定的值(如s+/-1),由于它们的作用,最近引起了越来越多的兴趣在高效、稳健或私人机器学习模型中。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators discuss new findings in Machine Learning. According to news originatingfrom St. Louis, Missouri, by New sRx correspondents, research stated, “Linear real-valued computationsover distr ibuted datasets are common in many applications, most notably as part of machine learninginference. In particular, linear computations that are quantized, i.e. , where the coefficients are restrictedto a predetermined set of values (such a s +/- 1), have gained increasing interest lately due to their rolein efficient, robust, or private machine learning models.”
NETL
NSTL