🎥 When science fiction becomes the tester's reality: deep learning and IoT testing
👁 1 раз ⏳ 1495 сек.
Jaroslaw Hryszko's talk at SQA Days-25 conference. May 31-June 1. Saint Petersburg. Russia
www.sqadays.com

Deep Learning with Keras - Python

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
- Deep Learning with Keras and Python (Course Introduction)
- Convolutional Neural Networks (CNN) in Keras - Python
- Word2vec with Gensim - Python
- Recurrent Neural Networks (RNN / LSTM )with Keras - Python
- LSTM input output shape , Ways to improve accuracy of predictions in Keras
- Deep Learning Chatbot using Keras and Python - Part I (Pre-processing text for inputs into LSTM)
- Deep Learning Chatbot using Keras and Python - Part 2 (Text/word2vec inputs into LSTM)
- Activation Functions in Neural Networks (Sigmoid, ReLU, tanh, softmax)
- Object Recognition App for Visually Impaired
- Perceptron and Gradient Descent Algorithm - Scikit learn
- Neural Networks and Backpropogation Scikit learn

#video

🎥 Deep Learning with Keras and Python (Course Introduction)
👁 1 раз ⏳ 100 сек.
Deep Learning has been a hot area of interest. Through this series we start learning some famous deep learning models like Deep Neural Networks, Re...

🎥 Convolutional Neural Networks (CNN) in Keras - Python
👁 1 раз ⏳ 756 сек.
In this tutorial we learn to make a convnet or Convolutional Neural Network or CNN in python using keras library with theano backend. It is okay if...

🎥 Word2vec with Gensim - Python
👁 1 раз ⏳ 557 сек.
This video explains word2vec concepts and also helps implement it in gensim library of python.

Word2vec extracts features from text and assigns v...

🎥 Recurrent Neural Networks (RNN / LSTM )with Keras - Python
👁 1 раз ⏳ 711 сек.
In this tutorial, we learn about Recurrent Neural Networks (LSTM and RNN). Recurrent neural Networks or RNNs have been very successful and popular...

🎥 LSTM input output shape , Ways to improve accuracy of predictions in Keras
👁 1 раз ⏳ 637 сек.
In this tutorial we look at how we decide the input shape and output shape for an LSTM.
We also tweak various parameters like Normalization, Activ...

🎥 Deep Learning Chatbot using Keras and Python - Part I (Pre-processing text for inputs into LSTM)
👁 1 раз ⏳ 384 сек.
This is the first part of tutorial for making our own Deep Learning or Machine Learning chat bot using keras.
In this video we pre-process a conv...

🎥 Deep Learning Chatbot using Keras and Python - Part 2 (Text/word2vec inputs into LSTM)
👁 1 раз ⏳ 486 сек.
This is the second part of tutorial for making our own Deep Learning or Machine Learning chat bot using keras.
In this video we input our pre-pr...

🎥 Activation Functions in Neural Networks (Sigmoid, ReLU, tanh, softmax)
👁 1 раз ⏳ 276 сек.
Activation Functions in Neural Networks are used to contain the output between fixed values and also add a non linearity to the output.

Activatio...

🎥 Object Recognition App for Visually Impaired
👁 1 раз ⏳ 65 сек.
This App was made for IBM I-Care Watson challenge by Sai Keshav Kolluru, Shreyans Shrimal and Sudharsan Krishnaswamy of IIT Bhubaneswar.

We used...

🎥 Perceptron and Gradient Descent Algorithm - Scikit learn
👁 1 раз ⏳ 425 сек.
The Perceptron Algorithm is generally used for classification and is much like the simple regression. The weights of the perceptron are trained usi...

​Is Deep Reinforcement Learning Really Superhuman on Atari?
https://arxiv.org/abs/1908.04683

🔗 Is Deep Reinforcement Learning Really Superhuman on Atari?
Consistent and reproducible evaluation of Deep Reinforcement Learning (DRL) is not straightforward. In the Arcade Learning Environment (ALE), small changes in environment parameters such as stochasticity or the maximum allowed play time can lead to very different performance. In this work, we discuss the difficulties of comparing different agents trained on ALE. In order to take a step further towards reproducible and comparable DRL, we introduce SABER, a Standardized Atari BEnchmark for general Reinforcement learning algorithms. Our methodology extends previous recommendations and contains a complete set of environment parameters as well as train and test procedures. We then use SABER to evaluate the current state of the art, Rainbow. Furthermore, we introduce a human world records baseline, and argue that previous claims of expert or superhuman performance of DRL might not be accurate. Finally, we propose Rainbow-IQN by extending Rainbow with Implicit Quantile Networks (IQN) leading to new state-of-the-art

🎥 Automatic Mathematics
👁 1 раз ⏳ 842 сек.
There are 7 math problems that each have a 1 million dollar prize attached to them by the Clay Mathematics Institute. Only 1 of these problems have been solved so far, meaning the other 6 are open to anyone in the world with the proper motivation to solve. In this episode, I'm going to explain how recent advancements in Artificial Intelligence can help an individual solve these problems and possibly win the prize money. There are 2 specific techniques I have in mind, the newly released "Ramanujan Machine" w

​Tesla is going to win Level 5 - George Hotz

🔗 Tesla is going to win Level 5 - George Hotz
This is a clip from a conversation with George Hotz on the Artificial Intelligence podcast. You can watch the full conversation here: http://bit.ly/2YLIPom If you enjoy these, consider subscribing, sharing, and commenting below. Full episode: http://bit.ly/2YLIPom Podcast website: https://lexfridman.com/ai George Hotz is the founder of Comma.ai, a machine learning based vehicle automation company. He is an outspoken personality in the field of AI and technology in general. He first gained recognition for

​Использование сентиментного анализа применительно к биржевым торговым роботам
https://habr.com/ru/post/463509/

🔗 Использование сентиментного анализа применительно к биржевым торговым роботам
Здравствуйте, дамы и господа. Хотел бы поделиться с вами своими мыслями относительно программ для автоматизированной торговли на бирже, в частности, применение...

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🎥 Python Flappy Bird AI Tutorial (with NEAT) - Pixel Perfect Collision w/ Pygame
👁 1 раз ⏳ 1161 сек.
This python flappy bird AI tutorial will cover creating moving pipes on the screen as well as implementing pixel perfect collision between our birds and pipes. This is an example of using pygame masks to accomplish pixel perfect collision with pygame.

Image Download: https://techwithtim.net/wp-content/uploads/2019/08/imgs.zip
Code Download: https://github.com/techwithtim/NEAT-Flappy-Bird

Enroll in The Fundamentals of Programming w/ Python
https://tech-with-tim.teachable.com/p/the-fundamentals-of-programm

🎥 "Probabilistic Programming and Bayesian Inference in Python" - Lara Kattan (Pyohio 2019)
👁 1 раз ⏳ 5463 сек.
Lara Kattan

https://www.pyohio.org/2019/presentations/116

Let's build up our knowledge of probabilistic programming and Bayesian inference! All you need to start is basic knowledge of linear regression; familiarity with running a model of any type in Python is helpful.

By the end of this presentation, you'll know the following:
- What probabilistic programming is and why it's necessary for Bayesian inference
- What Bayesian inference is, how it's different from classical frequentist inference, and

​Particle Filter : A hero in the world of Non-Linearity and Non-Gaussian

🔗 Particle Filter : A hero in the world of Non-Linearity and Non-Gaussian
The superiority of particle filter technology in nonlinear and non-Gaussian systems determines its wide range of applications. In addition…

​The Symmetry and Asymmetry of Baseball’s Graph
To derive insights about baseball, many analysts use a Markov chain model to describe the game.
https://towardsdatascience.com/the-symmetry-and-asymmetry-of-baseballs-graph-d2b18fd194d1?source=collection_home---4------1-----------------------

🔗 The Symmetry and Asymmetry of Baseball’s Graph
To derive insights about baseball, many analysts use a Markov chain model to describe the game. While a modeler could pose such a chain in…

​4 must-have паттерна проектирования в Python

#DataMining

Пишете на Python и не знаете, с какого паттерна проектирования начать?
В статье разбор популярных шаблонов с примерами кода на Python.
https://habr.com/ru/post/463731/

🔗 4 must-have паттерна проектирования в Python
Пишете на Python и не знаете, с какого паттерна проектирования начать? В статье разбор популярных шаблонов с примерами кода на Python. Абстрактная фабрика Не...

​Big data в переводческой отрасли: как это работает, реалии и перспективы – популярная тематическая секция в рамках технологического потока 10-го юбилейного Translation Forum Russia - 2019.

Организатор – группа компаний ЭГО Транслейтинг – один из лидеров лингвистического рынка России.

Различные аспекты обработки и анализа данных в переводческой отрасли в сравнении с другими областями. Возможность применения технологии блокчейн. Сложные вопросы работы с большими базами данных при координации работ по переводу. Адаптивный машинный перевод: от чего зависит качество? Поменяет ли технология ландшафт переводческой отрасли?

Обсуждение этих и других «горячих» тем, а также официальная презентация EGOTECH - технологической платформы, предоставляющей решения обработки текста и контроля качества перевода – на секции, посвященной big data в переводческой отрасли.

Спикеры: Елизавета Иванова (R&D директор Компании ЭГО Транслейтинг), Максим Ковалев (генеральный директор IQ Systems), Татьяна Попова (руководитель отдела переводов АО Группа Илим); Юлия Епифанцева (директор по развитию Promt), Никита Ткачев (менеджер по развитию ML продуктов Яндекс.Облака), Павел Доронин (продакт-менеджер Smartcat). Модератор секции – Евгения Городецкая, вице-президент по технологическому развитию группы компаний ЭГО Транслейтинг.

Секция состоится 24 августа с 10.00 до 12.00 на площадке Российского государственного педагогического университета имени А.И. Герцена (Казанская улица, 3а, корпус 5, «Дискуссионный зал»).

Регистрация по ссылке: http://tconference.ru/account/#tab-register

Ждём вас! Будет интересно😎

#EGOTranslating #ЭГОТранслейтинг #TFRUS #TFR10yearschallenge
#TranslationForumRussia #TFR2019

​Mesh R-CNN
Rapid advances in 2D perception have led to systems that accurately detect
https://arxiv.org/abs/1906.02739

🔗 Mesh R-CNN
Rapid advances in 2D perception have led to systems that accurately detect objects in real-world images. However, these systems make predictions in 2D, ignoring the 3D structure of the world. Concurrently, advances in 3D shape prediction have mostly focused on synthetic benchmarks and isolated objects. We unify advances in these two areas. We propose a system that detects objects in real-world images and produces a triangle mesh giving the full 3D shape of each detected object. Our system, called Mesh R-CNN, augments Mask R-CNN with a mesh prediction branch that outputs meshes with varying topological structure by first predicting coarse voxel representations which are converted to meshes and refined with a graph convolution network operating over the mesh's vertices and edges. We validate our mesh prediction branch on ShapeNet, where we outperform prior work on single-image shape prediction. We then deploy our full Mesh R-CNN system on Pix3D, where we jointly detect objects and predict their 3D shapes.

​How technology impacts the way of producing and consuming food at AGRO & TECH conference by Sistema_VC

Founders of startups from the UK, the Netherlands and Russia will talk about how AI provides people with better nutrition and globally helps fighting hunger. You will learn how agriculture and tech interact and network with startup founders, innovation managers, investors and the media in the industry.

Place: Moscow, Kollektiv Space, Bol'shoy Znamenskiy 2s3, metro Kropotkinskaya
Date: August 21st, 6 pm
Register free: https://is.gd/JgvmUA

🔗 #PUBLIC_TECH / AGRO & TECH
Конференция о технологиях в сельском хозяйстве.

Евгений Разинков. Лекция 10. Кластеризация (курс "Машинное обучение, весна 2019)
https://www.youtube.com/watch?v=lEUTG6s5YhY

🎥 Евгений Разинков. Лекция 10. Кластеризация (курс "Машинное обучение, весна 2019)
👁 1 раз ⏳ 3608 сек.
Лекция посвящена алгоритмам кластеризации. Рассмотрены следующие вопросы:
- Постановка задачи кластеризации.
- Алгоритм k-means.
- Целевая функция алгоритма k-means.
- Вывод формул обновления весов из целевой функции.
- Агломеративная кластеризация.
- Способы вычисления расстояния между кластерами: Single-Link, Average-Link, Complete-Link.

Евгений Разинков -- к.ф.-м.н., руководитель отдела машинного обучения и компьютерного зрения Группы компаний FIX, ассистент кафедры системного анализа и ИТ института ВМи

​Awesome Machine Learning
A curated list of awesome machine learning frameworks, libraries and software (by language).

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
libraries: https://github.com/josephmisiti/awesome-machine-learning

books: https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md

🔗 josephmisiti/awesome-machine-learning
A curated list of awesome Machine Learning frameworks, libraries and software. - josephmisiti/awesome-machine-learning

​Data Science Simplified Part 12: Resampling Methods

🔗 Data Science Simplified Part 12: Resampling Methods
Concept

​Building a Vocal Emotion Sensor with Deep Learning
Teaching machines to better understand human communication

https://towardsdatascience.com/building-a-vocal-emotion-sensor-with-deep-learning-bedd3de8a4a9?source=topic_page---------------------------20

🔗 Building a Vocal Emotion Sensor with Deep Learning
Teaching machines to better understand human communication

🎥 17. Bayesian Statistics
👁 1 раз ⏳ 4685 сек.
MIT 18.650 Statistics for Applications, Fall 2016
View the complete course: http://ocw.mit.edu/18-650F16
Instructor: Philippe Rigollet

In this lecture, Prof. Rigollet talked about Bayesian approach, Bayes rule, posterior distribution, and non-informative priors.

License: Creative Commons BY-NC-SA
More information at http://ocw.mit.edu/terms
More courses at http://ocw.mit.edu

🎥 35. Finding Clusters in Graphs
👁 1 раз ⏳ 2089 сек.
MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018
Instructor: Gilbert Strang
View the complete course: https://ocw.mit.edu/18-065S18
YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP63oMNUHXqIUcrkS2PivhN3k

The topic of this lecture is clustering for graphs, meaning finding sets of 'related' vertices in graphs. The challenge is finding good algorithms to optimize cluster quality. Professor Strang reviews some possibilities.

License: Creative

🎥 33. Neural Nets and the Learning Function
👁 1 раз ⏳ 3367 сек.
MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018
Instructor: Gilbert Strang
View the complete course: https://ocw.mit.edu/18-065S18
YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP63oMNUHXqIUcrkS2PivhN3k

This lecture focuses on the construction of the learning function F, which is optimized by stochastic gradient descent and applied to the training data to minimize the loss. Professor Strang also begins his review of distance matrices.

Lic