CMU11-777 multimodal machine learning Fall 2019讲义
上传者不拥有讲义的原始版权。所有版权归属CMU。
该文件集是CMU开设的11-777课程，名为multimodal machine learning，每年fall学期开设。
本讲义是2019 Fall的版本。
课程介绍：
Description
Multimodal machine learning (MMML) is a vibrant multi-disciplinary research field which addresses some of the original goals of artificial intelligence by integrating and modeling multiple communicative modalities, including linguistic, acoustic and visual messages. With the initial research on audio-visual speech recognition and more recently with language vision projects such as image and video captioning, this research field brings some unique challenges for multimodal researchers given the heterogeneity of the data and the contingency often found between modalities. The course will present the fundamental mathematical concepts in machine learning and deep learning relevant to the five main challenges in multimodal machine learning: (1) multimodal representation learning, (2) translation mapping, (3) modality alignment, (4) multimodal fusion and (5) co-learning. These include, but not limited to, multimodal auto-encoder, deep canonical correlation analysis, multi-kernel learning, attention models and multimodal recurrent neural networks. We will also review recent papers describing state-of-the-art probabilistic models and computational algorithms for MMML and discuss the current and upcoming challenges. The course will discuss many of the recent applications of MMML including multimodal affect recognition, image and video captioning and cross-modal multimedia retrieval. This is a graduate course designed primarily for PhD and research master students at LTI, MLD, CSD, HCII and RI; others, for example (undergraduate) students of CS or from professional master programs, are advised to seek prior permission of the instructor. It is required for students to have taken an introduction machine learning course such as 10-401, 10-601, 10-701, 11-663, 11-441, 11-641 or 11-741. Prior knowledge of deep learning is recommended.
该文件集是CMU开设的11-777课程，名为multimodal machine learning，每年fall学期开设。
本讲义是2019 Fall的版本。
课程介绍：
Description
Multimodal machine learning (MMML) is a vibrant multi-disciplinary research field which addresses some of the original goals of artificial intelligence by integrating and modeling multiple communicative modalities, including linguistic, acoustic and visual messages. With the initial research on audio-visual speech recognition and more recently with language vision projects such as image and video captioning, this research field brings some unique challenges for multimodal researchers given the heterogeneity of the data and the contingency often found between modalities. The course will present the fundamental mathematical concepts in machine learning and deep learning relevant to the five main challenges in multimodal machine learning: (1) multimodal representation learning, (2) translation mapping, (3) modality alignment, (4) multimodal fusion and (5) co-learning. These include, but not limited to, multimodal auto-encoder, deep canonical correlation analysis, multi-kernel learning, attention models and multimodal recurrent neural networks. We will also review recent papers describing state-of-the-art probabilistic models and computational algorithms for MMML and discuss the current and upcoming challenges. The course will discuss many of the recent applications of MMML including multimodal affect recognition, image and video captioning and cross-modal multimedia retrieval. This is a graduate course designed primarily for PhD and research master students at LTI, MLD, CSD, HCII and RI; others, for example (undergraduate) students of CS or from professional master programs, are advised to seek prior permission of the instructor. It is required for students to have taken an introduction machine learning course such as 10-401, 10-601, 10-701, 11-663, 11-441, 11-641 or 11-741. Prior knowledge of deep learning is recommended.
文件下载
资源详情
[{"title":"（ 21 个子文件 89.93MB ） CMU11-777 multimodal machine learning Fall 2019讲义","children":[{"title":"lecture10.1MultimodalFusion.pdf <span style='color:#111;'> 5.69MB </span>","children":null,"spread":false},{"title":"lecture2.2BasicConceptsOptimization.pdf <span style='color:#111;'> 2.35MB </span>","children":null,"spread":false},{"title":"lecture10.2NewDirections.pdf <span style='color:#111;'> 7.78MB </span>","children":null,"spread":false},{"title":"lecture7.1AlignmentAndRepresentation.pdf <span style='color:#111;'> 2.95MB </span>","children":null,"spread":false},{"title":"lecture2.1BasicConcepts.pdf <span style='color:#111;'> 2.25MB </span>","children":null,"spread":false},{"title":"lecture5.2StructuredRepresentations.pdf <span style='color:#111;'> 2.69MB </span>","children":null,"spread":false},{"title":"lecture1.1Introduction.pdf <span style='color:#111;'> 3.76MB </span>","children":null,"spread":false},{"title":"lecture4.1MultimodalRepresentations.pdf <span style='color:#111;'> 3.84MB </span>","children":null,"spread":false},{"title":"Lecture9.2VisualQuestionAnswering.pdf <span style='color:#111;'> 5.14MB </span>","children":null,"spread":false},{"title":"Lecture13.1Interpretable_Linear_ModelingGirard.pdf <span style='color:#111;'> 1.31MB </span>","children":null,"spread":false},{"title":"RL_Lecture_1.pdf <span style='color:#111;'> 4.04MB </span>","children":null,"spread":false},{"title":"Lecture12.2GenerativeModelsNeubig.pdf <span style='color:#111;'> 9.96MB </span>","children":null,"spread":false},{"title":"Lecture7.2GenerativeModels.pdf <span style='color:#111;'> 3.21MB </span>","children":null,"spread":false},{"title":"lecture9.1RandomFieldsAndMore.pdf <span style='color:#111;'> 2.43MB </span>","children":null,"spread":false},{"title":"RL_Lecture_2.pdf <span style='color:#111;'> 7.93MB </span>","children":null,"spread":false},{"title":"Lecture12.1EmbodiedLanguageGrounding.pdf <span style='color:#111;'> 19.19MB </span>","children":null,"spread":false},{"title":"lecture3.1ConvolutionNetwork.pdf <span style='color:#111;'> 3.65MB </span>","children":null,"spread":false},{"title":"lecture1.2datasets.pdf <span style='color:#111;'> 6.54MB </span>","children":null,"spread":false},{"title":"lecture4.2CoordinatedRepresentations.pdf <span style='color:#111;'> 3.25MB </span>","children":null,"spread":false},{"title":"lecture3.2RecurrentNetworks.pdf <span style='color:#111;'> 2.78MB </span>","children":null,"spread":false},{"title":"lecture5.1MultimodalAlignment.pdf <span style='color:#111;'> 2.84MB </span>","children":null,"spread":false}],"spread":true}]
评论信息
其他资源
- 高速电路pcb设计与emc技术分析
- PB 多选下拉列表框
- fragstats4.2安装包
- vissim4.3安装出现问题解决方案.doc
- 高通改串烧录
- webbrowser浏览器多标签
- lena--NS3仿真lte项目
- lm算法的matlab实现
- 单像空间后方交会c++程序代码
- Qt：Qt实现飞秋拦截助手—ARP攻击 完整项目代码
- 最新maven私服工具nexus.zip
- 基于边缘笔画特征结构的维吾尔笔迹鉴别
- S6B33B2_V1.5_20040308.pdf
- Geany编辑器官方最新版windows安装包
- ngtemplate-loader：将AngularJS模板包含在Webpack捆绑包中，并预加载模板缓存-源码
- PHPCMS V9.6.6 修改版
- bochs-2.4.5.tar.gz
- 产品经理产品规划书模版
- JSP+SQL水费管理系统
- 470 570 bios
- ASP.NET毕业设计(邮件收发+网站)
- VC++ 数字图像处理典型算法及实现 （源代码）
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明