Neural Networks | Нейронные сети
11.9K subscribers
755 photos
163 videos
170 files
9.41K links
Все о машинном обучении

По всем вопросам - @notxxx1

№ 4959169263
Download Telegram
🎥 Tiresias: Predicting Security Events Through Deep Learning
👁 1 раз 1427 сек.
Previous research in predicting malicious events only looked at binary outcomes (eg. whether an attack would happen or not), but not at the specific steps that an attacker would undertake. To fill this gap we present Tiresias xspace, a system that leverages Recurrent Neural Networks (RNNs) to predict future events on a machine, based on previous observations.
Read this paper in the ACM Digital Library: https://dl.acm.org/citation.cfm?id=3243811
🎥 10 глупых вопросов РУКОВОДИТЕЛЮ ЯНДЕКС.ПОИСКА
👁 6 раз 1173 сек.
Новый гость "10 глупых вопросов" – руководитель Поиска Яндекса Андрей Стыскин. Мы задали Андрею самые глупые вопросы о работе Поиска, личных данных и получили на них умные ответы.
Подписка Яндекс.Плюс на месяц (пробный период) для всех подписчиков канала ЖИЗА: https://ya.cc/52uOI

ЖИЗА в Instagram: https://www.instagram.com/zhiza_show

FAQ – почему мы не озвучиваем вопросы: https://goo.gl/X1mJZV

Другие выпуски «10 глупых вопросов»:
-ветеринар https://goo.gl/WBjJQd
-мультипликатор https://goo.gl/n7obfz
-пр
🎥 Neural networks interactively - right in your browser! - Piotr Migdał - code::dive 2018
👁 1 раз 3840 сек.
Deep learning (artificial neural networks) is progressing at a rapid pace. In the last few years, image recognition performance went from not useful to on a par with human level. Lately, AlphaGo Zero not only beat human masters, but was able to do so entirely learning by playing with itself. And it keeps going; something that was an original discovery 6 months ago may have become an industry baseline.

Moreover, it is relatively easy to start using deep learning - using Python libraries such as Keras or PyT
AI Learns Real-Time Defocus Effects in VR

Наш телеграмм канал - https://t.me/ai_machinelearning_big_data

https://www.youtube.com/watch?v=Ljgszx4tudo

🎥 AI Learns Real-Time Defocus Effects in VR
👁 1 раз 260 сек.
The paper "DeepFocus: Learned Image Synthesis for Computational Displays" and its source code is available here:
https://research.fb.com/publications/deepfocus-siggraph-asia-2018/
https://www.oculus.com/blog/introducing-deepfocus-the-ai-rendering-system-powering-half-dome/
https://github.com/facebookresearch/DeepFocus

Pick up cool perks on our Patreon page:
› https://www.patreon.com/TwoMinutePapers

We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
313V, Alex Haro,
​ABY3: A Mixed Protocol Framework for Machine Learning

🔗 ABY3: A Mixed Protocol Framework for Machine Learning
Machine learning is widely used to produce models for a range of applications and is increasingly offered as a service by major technology companies. However...
s this the BEST BOOK on Machine Learning? Hands On Machine Learning Review

🎥 Is this the BEST BOOK on Machine Learning? Hands On Machine Learning Review
👁 1 раз 331 сек.
Hands On Machine Learning with Scikit Learn and Tensorflow published by O'Reilly and written by Aurelien Geron could just be the best practical book on machine learning. In this review I explain why.

You can buy the book from my Amazon Page ►https://www.amazon.com/shop/pythonprogrammer (affiliate links)

►Subscribe to my YouTube Channel http://bit.ly/2LCdOy1

SUPPORT MY CHANNEL
►Buy me a coffee https://www.ko-fi.com/S6S7LZYP

Programming Learning Resources

Coursera https://www.coursera.org/specializations
🎥 Machine Learning With Tensor Flow | Recurrent Neural Networks | Part 3| Eduonix
👁 1 раз 980 сек.
A recurrent neural network (RNN) is a type of artificial neural network commonly used in speech recognition and natural language processing (NLP). RNNs are designed to recognize a data's sequential characteristics and use patterns to predict the next likely scenario. In this video, you will go through the Basics and give the overall explanation of what it is and how it works. Let's learn!!

Want to learn Machine Learning With TensorFlow in Detail? Check out our course Machine Learning With TensorFlow The Pr
​Тест Тьюринга на конференции OpenTalks.AI !

3-й всероссийский конкурс русскоговорящих чат-ботов в формате теста Тьюринга пройдет на конференции OpenTalks.AI! Конкурс организует «Лаборатория Наносемантика» и OpenTalks.AI при поддержке компании МТС, Серебряного партнера конференции!

Компании-победители получат призы:
• 1 место – 200,000 руб.
• 2 место – 150,000 руб.
• 3 место – 100,000 руб.

Каждый желающий может стать экспертом в этом конкурсе, для этого необходимо зарегистрироваться в Телеграм боте @TuringTestRussiaBot и в период с 14 по 16 февраля поговорить в этом чате с несколькими собеседниками и потом угадать, с кем Вы разговаривали – с человеком или ботом. Наиболее активные эксперты, которые угадают точнее всего, получат призы:
• 1 место – 20,000 руб.
• 2 место – 15,000 руб.
• 3 место – 10,000 руб.

Конкурс будет проходить 14-16 февраля, объявление результатов и награждение победителей состоится на конференции 16 февраля. Подробности и регистрация участников - на странице конкурса http://opentalks.ai/ru/turing-test

🔗 OpenTalks.AI - Тест Тьюринга
OpenTalks.AI - Тест Тьюринга
🎥 MERA - ML meetup - Jan 2019 - Погружение в Machine Learning. Участвуем в Kaggle соревнованиях!
👁 1 раз 1862 сек.
Выступление Антона Чивкунова на митапе MERA по машинному обучению. Когда ты начинаешь свой путь в области Data Science и Machine Learning, поражает обилие разных материалов для самостоятельного изучения, но без навыков применения все эти знания малого стоят. Где же взять этот опыт применения машинного обучения на реальных «взрослых» задачах? Тут нам на помощь приходит сервис Kaggle со своей облачной средой разработки/выполнения и действительно крутым сообществом Data Science инженеров. На примере участия в
I Built My Own Self-Driving Car. Part #3
In the last article, I have introduced you to a very simple lane detection with OpenCV. Taking into account the simplicity, it was doing well. However, it was not up to my expectations. Looks like the current solution that I am going to show you today does not get better unless you want switch to the Recurrent Convolutional Neural Networks (and this is exactly what I am up to). We are going to talk about a way to get better results based on the Hough Transform method output.

#programming #IT #artificialintellegence #developer #HaarCascade #Python #OpenCV #MadDevs

https://blog.maddevs.io/i-built-my-own-self-driving-car-part-3-1ca1d85e9d59

🔗 I Built My Own Self-Driving Car. Part #3 – Mad Devs
I Built My Own Self-Driving Car. Part #2

In my last article, I have played around with OpenCV and Haar Cascade Classifier in order to detect vehicles. It did not perform very well though. There were many false predictions and the FPS could not get above 15. Today I will introduce you to the third version of the YOLO algorithm developed for the Darknet and ported to Tensorflow and Keras so we can use a nice and shiny Python environment. We are not going to train our own model today and use pre-trained weights.

#programming #IT #artificialintellegence #developer #HaarCascade #Python #OpenCV #MadDevs

https://blog.maddevs.io/i-built-my-own-self-driving-car-part-2-e3894ce4eb42

🔗 I Built My Own Self-Driving Car. Part #2 – Mad Devs
​New interesting research from Facebook about simulating focus effect with DNN
https://research.fb.com/publications/deepfocus-siggraph-asia-2018/

🔗 DeepFocus: Learned Image Synthesis for Computational Displays
In this paper, we introduce DeepFocus, a generic, end-to-end convolutional neural network designed to efficiently solve the full range of computational tasks for accommodation-supporting HMDs. This network is demonstrated to accurately synthesize defocus blur, focal stacks, multilayer decompositions, and multiview imagery using only commonly available RGB-D images, enabling real-time, near-correct depictions of retinal blur with a broad set of accommodation-supporting HMDs.
Applied Deep Learning with PyTorch - Full Course

🎥 Applied Deep Learning with PyTorch - Full Course
👁 1 раз 20404 сек.
In this course you will learn the key concepts behind deep learning and how to apply the concepts to a real-life project using PyTorch and Python.

You'll learn the following:
⌨️ RNNs and LSTMs
⌨️ Sequence Modeling
⌨️ PyTorch
⌨️ Building a Chatbot in PyTorch

⭐️Requirements ⭐️
⌨️ Some Basic High School Mathematics
⌨️ Some Basic Programming Knowledge
⌨️ Some basic Knowledge about Neural Networks

⭐️Contents ⭐️
⌨️ (0:00:08) Recurrent Nerual Networks - RNNs and LSTMs
⌨️ (0:35:54) Sequence-To-Sequence Models
⌨️
​Hands-On with Unsupervised Learning
A quick tutorial on k-means clustering and principal component analysis (PCA).

🔗 Hands-On with Unsupervised Learning – Towards Data Science
A quick tutorial on k-means clustering and principal component analysis (PCA).