隐马尔可夫模型(Hidden Markov Model,HMM)是统计模型,它用来描述一个含有隐含未知参数的马尔可夫过程。其难点是从可观察的参数中确定该过程的隐含参数。然后利用这些参数来作进一步的分析,例如模式识别。 其是在被建模的系统被认为是一个马尔可夫过程与未观测到的(隐藏的)的状态的统计马尔可夫模型。

VIP内容

报告题目:

Deep Reinforcement Learning for Computer Vision

报告简介:

近年来,深度强化学习作为机器学习的基本技术之一得到了发展,并成功地应用于各种计算机视觉任务(表现出最先进的性能)。在本教程中,我们将概述深度强化学习技术的趋势,并讨论如何使用它们来提高各种计算机视觉任务的性能(解决计算机视觉中的各种问题)。首先,我们简要介绍了深度强化学习的基本概念,并指出了在不同的计算机视觉任务中所面临的主要挑战。其次,介绍了一些用于计算机视觉任务的深度强化学习技术及其种类:策略学习、注意感知学习、不可微优化和多智能体学习。第三,介绍了深度强化学习在计算机视觉不同领域的应用。最后,我们将讨论深度强化学习中的一些开放性问题,以说明未来如何进一步发展更先进的计算机视觉算法。

嘉宾介绍:

Jiwen Lu,副教授,中国清华大学,自动化系。清华大学自动化系副教授,2015.11-至今,新加坡高级数字科学中心研究科学家,2011.3-2015.11,2003.7-2007.7西安理工大学信息科学系助理讲师。

Liangliang Ren ,清华大学博士生,研究方向是计算机视觉与机器学习、度量学习与深度强化学习

成为VIP会员查看完整内容
0
39

最新论文

Stochastic modelling is an essential component of the quantitative sciences, with hidden Markov models (HMMs) often playing a central role. Concurrently, the rise of quantum technologies promises a host of advantages in computational problems, typically in terms of the scaling of requisite resources such as time and memory. HMMs are no exception to this, with recent results highlighting quantum implementations of deterministic HMMs exhibiting superior memory and thermal efficiency relative to their classical counterparts. In many contexts however, non-deterministic HMMs are viable alternatives; compared to them the advantages of current quantum implementations do not always hold. Here, we provide a systematic prescription for constructing quantum implementations of non-deterministic HMMs that re-establish the quantum advantages against this broader class. Crucially, we show that whenever the classical implementation suffers from thermal dissipation due to its need to process information in a time-local manner, our quantum implementations will both mitigate some of this dissipation, and achieve an advantage in memory compression.

0
0
下载
预览
Top