Первый AI meetup от Russia.AI: технологии, платформы, интерфейсы и бизнес-кейсы.
Технологические аспекты:
* "Нейротехнологии. Глубокое обучение, DeepLearning», Владислав Беляев, DeepHackLab;
http://media.wix.com/ugd/d1d481_506c12d3c10d4ce5a6112bcb41e1d750.pdf
Платформы и интерфейсы:
* «История и будущее цифровых рабочих сред - Что дальше после Siri и Cortana", Даниил Корнев, Zet Universe;
http://media.wix.com/ugd/d1d481_ff234b6f8fc04267814fd4120df7aaa5.pdf
* "Боты: платформы и технологии», Павел Осадчук, ChatFirst;
http://media.wix.com/ugd/d1d481_b94c3b819e62444988f3af458ebdb9be.pdf
Бизнес-приложения:
* "Как информационные технологии изменили одну из самых консервативных отраслей России", (Право ру), Кирилл Kondtatenko, Pravo.ru;
http://media.wix.com/ugd/d1d481_7a2b417469f54e0bb1b0e7411d3e1461.pdf
Полная статья:
http://www.russia.ai/single-post/2016/08/28/The-first-AI-meetup-by-RussiaAI-technology-platforms-interfaces-and-business-cases
Технологические аспекты:
* "Нейротехнологии. Глубокое обучение, DeepLearning», Владислав Беляев, DeepHackLab;
http://media.wix.com/ugd/d1d481_506c12d3c10d4ce5a6112bcb41e1d750.pdf
Платформы и интерфейсы:
* «История и будущее цифровых рабочих сред - Что дальше после Siri и Cortana", Даниил Корнев, Zet Universe;
http://media.wix.com/ugd/d1d481_ff234b6f8fc04267814fd4120df7aaa5.pdf
* "Боты: платформы и технологии», Павел Осадчук, ChatFirst;
http://media.wix.com/ugd/d1d481_b94c3b819e62444988f3af458ebdb9be.pdf
Бизнес-приложения:
* "Как информационные технологии изменили одну из самых консервативных отраслей России", (Право ру), Кирилл Kondtatenko, Pravo.ru;
http://media.wix.com/ugd/d1d481_7a2b417469f54e0bb1b0e7411d3e1461.pdf
Полная статья:
http://www.russia.ai/single-post/2016/08/28/The-first-AI-meetup-by-RussiaAI-technology-platforms-interfaces-and-business-cases
Подборка курсов и ресурсов по глубокому обучению.
https://omtcyfz.github.io/2016/08/29/Deep-Learning-Resources.html
https://omtcyfz.github.io/2016/08/29/Deep-Learning-Resources.html
Визуализации: кто такой Data Scientist и классификация алгоритмов Машинного Обучения.
LSTMVis - Visual Analysis for Recurrent Neural Networks
LSTMVis a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows a user to select a hypothesis input range to focus on local state changes, to match these states changes to similar patterns in a large data set, and to align these results with structural annotations from their domain. We provide data for the tool to analyze specific hidden state properties on dataset containing nesting, phrase structure, and chord progressions, and demonstrate how the tool can be used to isolate patterns for further statistical analysis.
http://lstm.seas.harvard.edu/
LSTMVis a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows a user to select a hypothesis input range to focus on local state changes, to match these states changes to similar patterns in a large data set, and to align these results with structural annotations from their domain. We provide data for the tool to analyze specific hidden state properties on dataset containing nesting, phrase structure, and chord progressions, and demonstrate how the tool can be used to isolate patterns for further statistical analysis.
http://lstm.seas.harvard.edu/
Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks
This project is a baseline in the activity classification and its temporal location, focused on the ActivityNet Challenge. Here is detailed all the process of our proposed pipeline, as well the trained models and the utility to classify and temporally localize activities on new videos given. All the steps have been detailed, from downloading the dataset, to predicting the temporal locations going through the feature extraction and also the training.
https://imatge-upc.github.io/activitynet-2016-cvprw/
https://github.com/imatge-upc/activitynet-2016-cvprw
https://www.youtube.com/watch?v=3G-Vdmsluw0
#keras #video #activity #cvprw
This project is a baseline in the activity classification and its temporal location, focused on the ActivityNet Challenge. Here is detailed all the process of our proposed pipeline, as well the trained models and the utility to classify and temporally localize activities on new videos given. All the steps have been detailed, from downloading the dataset, to predicting the temporal locations going through the feature extraction and also the training.
https://imatge-upc.github.io/activitynet-2016-cvprw/
https://github.com/imatge-upc/activitynet-2016-cvprw
https://www.youtube.com/watch?v=3G-Vdmsluw0
#keras #video #activity #cvprw