​Natural Image Matting via Guided Contextual Attention

Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. Many of these methods can generate visually plausible alpha estimations, but typically yield blurry structures or textures in the semitransparent area... (read more)

https://github.com/Yaoyi-Li/GCA-Matting

Paper: https://arxiv.org/abs/2001.04069v1

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Yaoyi-Li/GCA-Matting
Natural Image Matting via Guided Contextual Attention - Yaoyi-Li/GCA-Matting

​Using neural networks to solve advanced mathematics equations

https://ai.facebook.com/blog/using-neural-networks-to-solve-advanced-mathematics-equations/

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Using neural networks to solve advanced mathematics equations
Facebook AI has developed the first neural network that uses symbolic reasoning to solve advanced mathematics problems.

​Run a TensorFlow SavedModel in Node.js directly without conversion

https://blog.tensorflow.org/2020/01/run-tensorflow-savedmodel-in-nodejs-directly-without-conversion.html

🔗 Run a TensorFlow SavedModel in Node.js directly without conversion

​Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study

Paper: https://arxiv.org/abs/2001.03844v1

Code https://github.com/pfliu-nlp/Named-Entity-Recognition-NER-Papers

🔗 pfliu-nlp/Named-Entity-Recognition-NER-Papers
An elaborate and exhaustive paper list for Named Entity Recognition (NER) - pfliu-nlp/Named-Entity-Recognition-NER-Papers

​Solutions - KaggleDB

🔗 Solutions - KaggleDB

​Anomaly Detection with Autoencoders in TensorFlow 2.0
A Guide on how to implement Neural Networks in TensorFlow 2.0 to detect anomalies.

🔗 Anomaly Detection with Autoencoders in TensorFlow 2.0
A Guide on how to implement Neural Networks in TensorFlow 2.0 to detect anomalies.

🎥 Deep Learning for Anime & Manga, by Vie Jill-Jênn [INRIA & Mangaki]
👁 3 раз ⏳ 1379 сек.

​On the Relationship between Self-Attention and Convolutional Layers

https://github.com/epfml/attention-cnn

Paper: https://arxiv.org/abs/1911.03584v2

🔗 epfml/attention-cnn
Source code for "On the Relationship between Self-Attention and Convolutional Layers" - epfml/attention-cnn

​Mapping the tech world with t-SNE

🔗 Mapping the tech world with t-SNE
We analyse 200k tech news articles with the t-SNE algorithm

​Physical Theory of Intelligence

🔗 Physical Theory of Intelligence
v1.0

​An extensible Evolutionary Algorithm Example in Python

🔗 An extensible Evolutionary Algorithm Example in Python
Learning how to write an easy Evolutionary Algorithm from scratch in less than 50 lines of code that you can use for your projects.

🎥 DeepPhish: Simulating Malicious AI
👁 1 раз ⏳ 3054 сек.
91% of cybercrimes and attacks start with a phishing email. This means that cyber security researchers must focus on detecting phishing in all of its settings and uses. However, they face many challenges as they go up against sophisticated and intelligent attackers. As a result, they must use cutting-edge Machine Learning and Artificial Intelligence techniques to combat existing and emerging criminal tactics.

By Alejandro Correa Bahnsen

Full Abstract & Presentation Materials: https://www.blackhat.com/eu-1

​PyTorch 1.4 release

https://github.com/pytorch/pytorch/releases/tag/v1.4.0

- PyTorch Mobile - Build level customization
- Distributed Model Parallel Training (RPC)
- Java bindings
- End of python 2 support =)
- Pruning out-of-the box
- Learning rate schedulers (torch.optim.lr_scheduler) now support “chaining.”
- Named Tensors (out of beta?)
- AMD Support (!?)
- Quantization (!) - more modules support

🔗 pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration - pytorch/pytorch

​Deep Image Compression using Decoder Side Information

Code: https://github.com/ayziksha/DSIN

Paper: https://arxiv.org/abs/2001.04753v1

🔗 ayziksha/DSIN
Deep Image Compression using Decoder Side Information - ayziksha/DSIN

​Глубокое обучение / Deep Learning

1. Слои глубоких сверточных сетей
2. Alex (net)
3. VGG
4. GoogleNet
5. ResNet, InceptionResNet, DenseNet
6. SqueezeNet

#video #neural

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Открыть в Telegram



🎥 Untitled
👁 1 раз ⏳ 1061 сек.


🎥 Untitled
👁 1 раз ⏳ 330 сек.


🎥 Untitled
👁 1 раз ⏳ 198 сек.


🎥 Untitled
👁 1 раз ⏳ 275 сек.


🎥 Untitled
👁 1 раз ⏳ 320 сек.


🎥 Untitled
👁 1 раз ⏳ 129 сек.

​#MoscowTravelHack #DataScience #ПредиктивнаяАналитика

Задачи для DataSience-команд и аналитиков в рамках хакатона Moscow Travel Hack. Создай предиктивную модель покупки билета на основе данных о пользователе в сервисе «Мегафон Путешествия» или придумай рекомендательный сервис, который сможет построить индивидуальную программу посещения Москвы для иностранного туриста на платформе Russpass.

Эти и другие 10 задач можно найти на сайте хакатона travelhack.moscow
Призовой фонд — 1,1 млн рублей!

🔗 Moscow Travel Hack
Создай новые технологии и digital-решения для туризма. Призовой фонд 1.1 миллион рублей. Прием заявок до 28 января.

http://www.youtube.com/watch?v=00LoMxKY-_A#action=share
Для тех, кого заинтересовала тема машинного обучения :)

🎥 А? Машинное обучение
👁 1 раз ⏳ 533 сек.
Большое спасибо https://vas3k.ru/blog/machine_learning/
Без его картинок и примеров я бы не справился.

​Bayesian Deep Learning Benchmarks
Oxford Applied and Theoretical Machine Learning Group : https://github.com/OATML/bdl-benchmarks
#Bayesian #Benchmark #DeepLearning

🔗 OATML/bdl-benchmarks
Bayesian Deep Learning Benchmarks. Contribute to OATML/bdl-benchmarks development by creating an account on GitHub.

​"Everybody’s Talkin’: Let Me Talk as You Want"
Paper pdf: https://arxiv.org/pdf/2001.05201.pdf
Github: https://wywu.github.io/projects/EBT/EBT.html
Youtube: https://youtu.be/tNPuAnvijQk
This paper presents a method to edit a target portrait footage by taking a sequence of audio as input to synthesize a photo-realistic video.

🔗

​The hyperparameter tuning problem in Bayesian Networks

🔗 The hyperparameter tuning problem in Bayesian Networks
In this history, we discuss the structural criteria to take into account when building models based on BN (Bayesian Network). We will…