Presented By O’Reilly and Intel AI
Put AI to work
April 10-11, 2018: Training
April 11-13, 2018: Tutorials & Conference
Beijing, CN

Deep reinforcement learning’s killer app: Intelligent control in real-world systems

This will be presented in English.

Mark Hammond (Microsoft)
13:1013:50 Friday, April 13, 2018
企业人工智能 (AI in the Enterprise), 英文讲话 (Presented in English)
Location: 多功能厅2(Function Room 2) Level: Intermediate
Secondary topics:  制造业与工业自动化 (Manufacturing and Industrial Automation), 增强学习(Reinforcement Learning)

必要预备知识 (Prerequisite Knowledge)

基础编程经验
General experience with programming

您将学到什么 (What you'll learn)

通过案例研究来了解应用深度强化学习的最佳使用场景和业务价值,并逐步了解如何构建、训练和部署模型到真实世界的系统里
Explore case studies to understand the best use cases and business impact of applied deep reinforcement learning and see step-by-step how to build, train, and deploy models onto real-world systems

描述 (Description)

本讲话将用英语授课,同时会提供中文同声传译。中文版本摘要会在英文摘要下面给出。

Reinforcement learning is a powerful machine learning technique for solving problems in dynamic and adaptive environments. Combined with a simulation or digital twin, reinforcement learning can train models to automate or optimize the efficiency of industrial systems and processes such as robotics, manufacturing, energy, and supply chain.

But what comes after the simulation? Mark Hammond dives into two real-world case studies to show how deep reinforcement learning successfully automated the machine tuning of a Fortune 500 manufacturing system and optimized energy efficiency of a large-scale HVAC system. Mark details the end-to-end process of building, training, and deploying models and examines the business impact of each application.


增强学习是解决动态变化和需要自适应的环境里问题的一个强有力的机器学习工具。结合了模拟或是数字的组合,增强学习能训练模型,让它们自动化或优化多种行业(例如机器人、制造业、能源、供应链)的系统和流程的效率。

但在模拟完后又要做什么?Mark Hammond将会详细介绍两个真实世界的案例,来展示增强学习是如何成功地自动化了一个财富500强制造业企业的机器调优,以及如何优化了一个大型空调企业的系统的能效。Mark将会详细介绍从构建、训练、部署模型到分析应用的业务影响的全过程。

Photo of Mark Hammond

Mark Hammond

Microsoft

Mark Hammond is cofounder and CEO at Bonsai. Mark has a deep passion for understanding how the mind works and has been thinking about AI throughout his career. He has held positions at Microsoft and numerous startups and in academia, including turns at Numenta and in the Yale Neuroscience Department. He holds a degree in computation and neural systems from Caltech.