Presented By
O’REILLY + INTEL AI

English中文
PUT AI TO WORK
June 18-21, 2019
Beijing, CN

Low precision inference on Intel Architecture

此演讲使用中文 (This will be presented in Chinese)

Lei Xia (Intel)
16:2017:00 Friday, June 21, 2019
实施人工智能 (Implementing AI)
Location: 多功能厅6A+B (Function Room 6A+B)

必要预备知识 (Prerequisite Knowledge)

Basic knowledge of AI and deep learning and interests in low precision inference for performance on Intel platform

您将学到什么 (What you'll learn)

How to get low precision inference acceleration on next Intel Xeon Platform

描述 (Description)

1. Brief introduction of low precision for AI inference
2. Introduce the Vector Neural Network Instructions(VNNI)
3. Introduce how to use the low precision inference acceleration with Intel Caffe, Tensorflow and OpenVINO

Photo of Lei Xia

Lei Xia

Intel

夏磊先生, 现任英特尔中国人工智能技术架构师,服务于英特尔数据中心技术销售部。专注于为客户在应用人工智能前沿技术过程中为客户的创新提供技术建议与指导提供,并提供英特尔产品与技术相关的支持。
夏磊先生于2000年加入英特尔,历任网络系统工程师、客户技术经理、渠道技术总监、云计算方案架构师、物联网端到端方案架构师,支持了国内信息产业在在互联网、数据中心、云计算与物联网术时代的持续技术创新。
夏磊先生获有机器人工程学士学位。在加入英特尔前任职于政府与教育行业的不同的技术开发和技术教育岗位,在软件算法、自动控制及工程管理等领域具有丰富经验。

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)