🎥 Machine learning for query optimization (Boston University MiDAS Seminar)
👁 1 раз ⏳ 4702 сек.
My seminar at Boston University on using machine learning for query optimization, including results from our Neo optimizer and future work.


BU MiDAS seminars: https://midas.bu.edu/seminar.html
Neo: https://rm.cab/neo
Slides: https://rm.cab/bu20

​New paper from FAIR. Authors show how to transfer DensePose from humans to animals w/o annotations in a self-training scenario.
asanakoy.github.io/densepose-evolution
youtu.be/OU3Ayg_l4QM
arxiv.org/abs/2003.00080
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Transferring Dense Pose to Proximal Animal Classes
Transferring Dense Pose to Proximal Animal Classes.


🎥 DensePose applied on chimps: comparison of our method before self-training (left) and after (right)
👁 1 раз ⏳ 31 сек.
Frame-by-frame predictions produced by our model before (teacher) and after self-training (student).
After self training the 24-class body part segmentation is more accurate and stable.

Project page: https://asanakoy.github.io/densepose-evolution/

​20 AI, Data Science, Machine Learning Terms You Need to Know in 2020 (Part 1) - KDnuggets

🔗 20 AI, Data Science, Machine Learning Terms You Need to Know in 2020 (Part 1) - KDnuggets
2020 is well underway, and we bring you 20 AI, data science, and machine learning terms we should all be familiar with as the year marches onward.

​TResNet: High Performance GPU-Dedicated Architecture

https://github.com/mrT23/TResNet/

https://arxiv.org/abs/2003.13630

🔗 mrT23/TResNet
TResNet: High Performance GPU-Dedicated Architecture - mrT23/TResNet

​Схема подделки, восстановления и проверки фруктов в овощном магазине. Отрывок из книги

🔗 Схема подделки, восстановления и проверки фруктов в овощном магазине. Отрывок из книги
Привет, Хаброжители! Пока такая ситуация за окном мы решили поделиться занимательным отрывком из нашей книги «Генеративное глубокое обучение. Творческий потенц...

🎥 Infoshare 2019: Mateusz Malinowski - From Images to Graphs: Modeling Invariances with Deep Learning
👁 1 раз ⏳ 2579 сек.
In recent years Deep Learning has become a dominant paradigm to learn representation for images and sequential data. Such a 'revolution' has started with the remarkable results on the ImageNet competition with AlexNet and has continued with more modern architectures like ResNet. Similarly, Recurrent Neural Networks are often used to represent language. Both types of architectures use different inductive biases that encode weight symmetries either on the grid (images) or on the chain (language), and more rec

🎥 Webinar #11 Next Generation Ultra High-Throughput Protein-Ligand Docking with Deep Learning
👁 1 раз ⏳ 3704 сек.
Recent studies have shown extending virtual screening libraries beyond hundreds of millions of compounds offers insights into new chemotypes, scaffolds, and binding motifs. In order to utilize the massive compute power available to research today, new techniques for analysis and screening are required. Standard techniques such as rigid structural docking are CPU bound and slow, and the analysis techniques are not designed to handle discrimination at the scale of billions of compounds. This webinar will cove

​Data Structures — Simplified and Classified

🔗 Data Structures — Simplified and Classified
This article will simplify and summarize these most essential data structures that you will understand and will be able to use easily.

​Scaling Machine Learning

🔗 Scaling Machine Learning
Razvan Peteanu | TMLS2019

🎥 NLP #6: The next generation of language models.
👁 1 раз ⏳ 5964 сек.
Mikhail Burtsev gives a talk about the problems of neural network architectures based on transformers (first of all, BERT and its variants) in relation to the task of language modeling, and offer research directions to overcome these problems.
Mikhail Burtsev is head of the DeepPavlov project & the Neural Networks and Deep Learning Lab of MIPT.

​Suphx: Mastering Mahjong with Deep Reinforcement Learning
Li et al.: https://arxiv.org/abs/2003.13590
#ArtificialIntelligence #DeepLearning #ReinforcementLearning

🔗 Suphx: Mastering Mahjong with Deep Reinforcement Learning
Artificial Intelligence (AI) has achieved great success in many domains, and game AI is widely regarded as its beachhead since the dawn of AI. In recent years, studies on game AI have gradually evolved from relatively simple environments (e.g., perfect-information games such as Go, chess, shogi or two-player imperfect-information games such as heads-up Texas hold'em) to more complex ones (e.g., multi-player imperfect-information games such as multi-player Texas hold'em and StartCraft II). Mahjong is a popular multi-player imperfect-information game worldwide but very challenging for AI research due to its complex playing/scoring rules and rich hidden information. We design an AI for Mahjong, named Suphx, based on deep reinforcement learning with some newly introduced techniques including global reward prediction, oracle guiding, and run-time policy adaptation. Suphx has demonstrated stronger performance than most top human players in terms of stable rank and is rated above 99.99% of all the officially ranked human players in the Tenhou platform. This is the first time that a computer program outperforms most top human players in Mahjong.

​Gradient Boosting with Scikit-Learn, XGBoost, LightGBM, and CatBoost - Machine Learning Mastery

🔗 Gradient Boosting with Scikit-Learn, XGBoost, LightGBM, and CatBoost - Machine Learning Mastery
Gradient boosting is a powerful ensemble machine learning algorithm. It's popular for structured predictive modeling problems, such as classification and regression on tabular data, and is often the main algorithm or one of the main algorithms used in winning solutions to machine learning competitions, like those on Kaggle. There are many implementations of gradient boosting available, including standard implementations in SciPy and

​Introducing the Model Garden for TensorFlow 2

Code examples for state-of-the-art models and reusable modeling libraries for TensorFlow 2.

https://blog.tensorflow.org/2020/03/introducing-model-garden-for-tensorflow-2.html

Model Garden repository: https://github.com/tensorflow/models/tree/master/official
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Introducing the Model Garden for TensorFlow 2

​How to Choose a Feature Selection Method For Machine Learning

https://machinelearningmastery.com/feature-selection-with-real-and-categorical-data/

🔗 How to Choose a Feature Selection Method For Machine Learning - Machine Learning Mastery
Feature selection is the process of reducing the number of input variables when developing a predictive model. It is desirable to reduce the number of input variables to both reduce the computational cost of modeling and, in some cases, to improve the performance of the model. Feature-based feature selection methods involve evaluating the relationship between each input variable and the target variable

🎥 Нейросеть учится играть в теннис (Часть 1) | ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ
👁 1 раз ⏳ 206 сек.
Это мое новое видео, посвященное искусственному интеллекту. В этом видео нейросеть учится играть в стилизованный теннис. Для этого проекта была применена нейросеть с шунтами из LSTM нейронов между скрытыми слоями, все технические подробности проекта будут рассказы позднее в отдельном видео.

♫Music By♫
●Waimis - Therapy [Bass Rebels Release]
●Song - https://youtu.be/HxKmQoygbQY

​Комплекс детекции курения по фото или видео на базе Intel NUC

🔗 Комплекс детекции курения по фото или видео на базе Intel NUC
В этом посте мы расскажем о том, как решали задачу определения факта курения посредством объектовой видеоаналитики на Intel NUC. На входе – видеопотоки с каме...

​Deep Learning Chatbot

🔗 Deep Learning Chatbot
What is a Deep Learning Chatbot? A deep learning chatbot learns right from scratch through a process called “Deep Learning.” In this process, the chatbot is created using machine learning algorithms. A deep learning chatbot learns everything from its data and human-to-human dialogue.

​Продуктовый аналитик: что делает, сколько зарабатывает, какую пользу несёт бизнесу

🔗 Продуктовый аналитик: что делает, сколько зарабатывает, какую пользу несёт бизнесу
Продуктовый аналитик — мостик между бизнесом и данными. Он работает рука об руку с продакт-менеджером и помогает продуктовой команде принимать верные решения. Ав...

​4-5 апреля пройдет отбор на онлайн-интенсивы в рамах фестиваля RuCode

🔗 4-5 апреля пройдет отбор на онлайн-интенсивы в рамах фестиваля RuCode
4-5 апреля пройдет отбор на онлайн-интенсивы в рамах фестиваля RuCode Это программа для начинающих в сфере спортивного программирования (дивизионы C и D) и иску...

🎥 How to Create Virtual Machine on Google Cloud Platform (GCP) | Create Virtual Machine using gcloud
👁 1 раз ⏳ 370 сек.
In this video, we'll be discussing how to create a Virtual Machine Using gcloud .
Google Cloud Platform (GCP), offered by Google, is a suite of cloud computing services that runs on the same infrastructure that Google uses internally for its end-user products, such as Google Search, Gmail and YouTube. Alongside a set of management tools, it provides a series of modular cloud services including computing, data storage, data analytics and machine learning. Registration requires a credit card or bank account d

Protecting Front line American Healthcare Workers Fighting COVID19: Lessons from South Korea
https://www.youtube.com/watch?v=JtDQkaTXC0A&feature=youtu.be

🎥 Protecting Front line American Healthcare Workers Fighting COVID19: Lessons from South Korea
👁 1 раз ⏳ 4065 сек.
This event is a Q&A session with Dr. Doo Ryeon Chung, MD PhD, Director of Infection Prevention and Control at Samsung Medical Center in Seoul, South Korea. He will be sharing key lessons and strategies for preventing COVID19 transmission within hospitals, including PPE standards, workflows, infrastructure, and workforce management.

The webinar is hosted by:
Ron C. Li, MD
Clinical Assistant Professor, Division of Hospital Medicine
Stanford University School of Medicine, Stanford, California
Twitter: @ronl