Lifelong Machine Learning and Sequential Decision Making for Natural Language Interfaces

自然语言界面的终身机器学习和顺序决策

基本信息

  • 批准号:
    312388-2013
  • 负责人:
  • 金额:
    $ 3.21万
  • 依托单位:
  • 依托单位国家:
    加拿大
  • 项目类别:
    Discovery Grants Program - Individual
  • 财政年份:
    2018
  • 资助国家:
    加拿大
  • 起止时间:
    2018-01-01 至 2019-12-31
  • 项目状态:
    已结题

项目摘要

What could be possible if we let a machine learn continuously over its lifetime? ****Objectives: The goal of this work is to develop lifelong learning algorithms with application to dialog management. At a theoretical level, this research will investigate and advance the principles by which a machine can gradually learn over a long period of time, discover new concepts and generalize concepts to new situations. This will be put in practice by developing open ended dialog systems for natural language interfaces. Personalization of such interfaces at the language level and adapting to the habits and preferences of the user will benefit tremendously from continuous learning.****Methods: Since continuous learning is a sequential process, the techniques developed will be in the framework of reinforcement learning. Particular emphasis will be put on the development of non-parametric techniques that do not make a closed world assumption by allowing new concepts (e.g., new words, expressions, habits, goals) to be discovered and represented on the fly. Hierarchical representations will be employed to organize and reason about the concepts from low level language units to high level user intentions. The techniques will be deployed in speech and text interfaces for smart phone applications.****Novelty and significance: Lifelong machine learning is a new research direction that remains vastly unexplored. This research will develop the theory and practice of this new paradigm, which will enable a new breed of intelligent systems. It will contribute to the next generation of natural user interfaces based on speech for smart phones, video-gaming and hands-free car consoles.**
如果我们让机器在其生命周期中不断学习,会有什么可能?*目标:这项工作的目标是开发应用于对话管理的终身学习算法。在理论层面,这项研究将探索和推进机器在很长一段时间内逐渐学习、发现新概念并将概念概括到新情况的原理。这将通过开发用于自然语言界面的开放式对话系统来实施。在语言层面使这种界面个性化并适应用户的习惯和偏好将极大地受益于持续学习。*方法:由于持续学习是一个连续的过程,因此所开发的技术将在强化学习的框架内进行。将特别强调非参数技术的发展,这种技术不会通过允许新概念(例如,新词、表达、习惯、目标)被动态地发现和表现来进行封闭的世界假设。将使用层次表示来组织和推理从低级语言单位到高级用户意图的概念。这些技术将被部署在智能手机应用的语音和文本界面中。*新颖性和意义:终身机器学习是一个新的研究方向,仍未得到极大的探索。这项研究将发展这一新范式的理论和实践,这将使新一代智能系统成为可能。它将为下一代基于语音的智能手机、视频游戏和免提汽车控制台的自然用户界面做出贡献。**

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Poupart, Pascal其他文献

Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks
前馈和循环和积网络的在线结构学习
Measuring Life Space in Older Adults with Mild-to-Moderate Alzheimer's Disease Using Mobile Phone GPS
  • DOI:
    10.1159/000355669
  • 发表时间:
    2014-01-01
  • 期刊:
  • 影响因子:
    3.5
  • 作者:
    Tung, James Yungjen;Rose, Rhiannon Victoria;Poupart, Pascal
  • 通讯作者:
    Poupart, Pascal
Automated handwashing assistance for persons with dementia using video and a partially observable Markov decision process
  • DOI:
    10.1016/j.cviu.2009.06.008
  • 发表时间:
    2010-05-01
  • 期刊:
  • 影响因子:
    4.5
  • 作者:
    Hoey, Jesse;Poupart, Pascal;Mihailidis, Alex
  • 通讯作者:
    Mihailidis, Alex

Poupart, Pascal的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Poupart, Pascal', 18)}}的其他基金

Robust and Sample Efficient Reinforcement Learning
鲁棒且样本高效的强化学习
  • 批准号:
    RGPIN-2019-05014
  • 财政年份:
    2022
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual
Robust and Sample Efficient Reinforcement Learning
鲁棒且样本高效的强化学习
  • 批准号:
    RGPIN-2019-05014
  • 财政年份:
    2021
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual
Robust and Sample Efficient Reinforcement Learning
鲁棒且样本高效的强化学习
  • 批准号:
    RGPIN-2019-05014
  • 财政年份:
    2020
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual
Reinforcement Learning for Sports Analytics
体育分析的强化学习
  • 批准号:
    521357-2018
  • 财政年份:
    2020
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Strategic Projects - Group
Reinforcement Learning for Sports Analytics
体育分析的强化学习
  • 批准号:
    521357-2018
  • 财政年份:
    2019
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Strategic Projects - Group
Robust and Sample Efficient Reinforcement Learning
鲁棒且样本高效的强化学习
  • 批准号:
    RGPIN-2019-05014
  • 财政年份:
    2019
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual
Lifelong Machine Learning and Sequential Decision Making for Natural Language Interfaces
自然语言界面的终身机器学习和顺序决策
  • 批准号:
    312388-2013
  • 财政年份:
    2017
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual
Lifelong Machine Learning and Sequential Decision Making for Natural Language Interfaces
自然语言界面的终身机器学习和顺序决策
  • 批准号:
    312388-2013
  • 财政年份:
    2016
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual
Lifelong Machine Learning and Sequential Decision Making for Natural Language Interfaces
自然语言界面的终身机器学习和顺序决策
  • 批准号:
    312388-2013
  • 财政年份:
    2015
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual
Lifelong Machine Learning and Sequential Decision Making for Natural Language Interfaces
自然语言界面的终身机器学习和顺序决策
  • 批准号:
    312388-2013
  • 财政年份:
    2014
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Discovery Grants Program - Individual

相似国自然基金

Understanding structural evolution of galaxies with machine learning
  • 批准号:
    n/a
  • 批准年份:
    2022
  • 资助金额:
    10.0 万元
  • 项目类别:
    省市级项目

相似海外基金

CAREER: Blessing of Nonconvexity in Machine Learning - Landscape Analysis and Efficient Algorithms
职业:机器学习中非凸性的祝福 - 景观分析和高效算法
  • 批准号:
    2337776
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Continuing Grant
RII Track-4:NSF: Physics-Informed Machine Learning with Organ-on-a-Chip Data for an In-Depth Understanding of Disease Progression and Drug Delivery Dynamics
RII Track-4:NSF:利用器官芯片数据进行物理信息机器学习,深入了解疾病进展和药物输送动力学
  • 批准号:
    2327473
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Standard Grant
CC* Campus Compute: UTEP Cyberinfrastructure for Scientific and Machine Learning Applications
CC* 校园计算:用于科学和机器学习应用的 UTEP 网络基础设施
  • 批准号:
    2346717
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Standard Grant
Learning to create Intelligent Solutions with Machine Learning and Computer Vision: A Pathway to AI Careers for Diverse High School Students
学习利用机器学习和计算机视觉创建智能解决方案:多元化高中生的人工智能职业之路
  • 批准号:
    2342574
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Standard Grant
Collaborative Research: Conference: DESC: Type III: Eco Edge - Advancing Sustainable Machine Learning at the Edge
协作研究:会议:DESC:类型 III:生态边缘 - 推进边缘的可持续机器学习
  • 批准号:
    2342498
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Standard Grant
Excellence in Research:Towards Data and Machine Learning Fairness in Smart Mobility
卓越研究:实现智能移动中的数据和机器学习公平
  • 批准号:
    2401655
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Standard Grant
I-Corps: Translation potential of using machine learning to predict oxaliplatin chemotherapy benefit in early colon cancer
I-Corps:利用机器学习预测奥沙利铂化疗对早期结肠癌疗效的转化潜力
  • 批准号:
    2425300
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Standard Grant
CAREER: Mitigating the Lack of Labeled Training Data in Machine Learning Based on Multi-level Optimization
职业:基于多级优化缓解机器学习中标记训练数据的缺乏
  • 批准号:
    2339216
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Continuing Grant
Postdoctoral Fellowship: OPP-PRF: Leveraging Community Structure Data and Machine Learning Techniques to Improve Microbial Functional Diversity in an Arctic Ocean Ecosystem Model
博士后奖学金:OPP-PRF:利用群落结构数据和机器学习技术改善北冰洋生态系统模型中的微生物功能多样性
  • 批准号:
    2317681
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Standard Grant
Accelerated discovery of ultra-fast ionic conductors with machine learning
通过机器学习加速超快离子导体的发现
  • 批准号:
    24K08582
  • 财政年份:
    2024
  • 资助金额:
    $ 3.21万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了