​Machine Learning — Diagnosing faults on vehicle fleet trackers

🔗 Machine Learning — Diagnosing faults on vehicle fleet trackers
A Data-Driven solution to diagnose faults on tracking modules.

🎥 Building a sustainable, open source machine learning platform for everyone (TensorFlow Meets)
👁 1 раз ⏳ 493 сек.
TensorFlow is a truly open source platform with over 1,900 contributors. On this episode of TensorFlow Meets, Laurence talks to Open Source Strategist Edd Wilder-James about how things like TensorFlow’s Request for Comments process, Special Interest Groups, and the modularity of its codebase make it easier for the ML community to build TensorFlow together. They also discuss the upcoming O’Reilly TensorFlow World conference, which is accepting applications to participate now through April 23rd. Please subscr

🎥 Lesson 2. Linear algebra basics
👁 1 раз ⏳ 1205 сек.
In order to understand the math behind the neural nets we need to recap the basics of linear algebra.

We will talk about such objects as vectors, matrcies and tensors.

Lecturer: Nadya Zueva (MIPT).

Materials:
https://drive.google.com/open?id=1iLiyNJSzIfgzTvnq1IHut-GXQcGgHVtm

---

About Deep Learning School at PSAMI MIPT

Official website: https://www.dlschool.org
Github-repo: https://github.com/DLSchool/dlschool_english

About PSAMI MIPT

Official website: https://mipt.ru/english/edu/phystechschool

​Как запустить ML-прототип за один день. Доклад Яндекс.Такси

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
Машинное обучение применяется на всём цикле заказа автомобиля в Яндекс.Такси, и число компонентов сервиса, работающих благодаря ML, постоянно растёт. Чтобы строить их единообразно, нам потребовался обособленный процесс. Руководитель службы машинного обучения и анализа данных Роман Халкечев рассказал про препроцессинг данных, применение моделей в продакшене, сервис их прототипирования и сопутствующие инструменты.
https://habr.com/ru/company/yandex/blog/447186/

🔗 Как запустить ML-прототип за один день. Доклад Яндекс.Такси
Машинное обучение применяется на всём цикле заказа автомобиля в Яндекс.Такси, и число компонентов сервиса, работающих благодаря ML, постоянно растёт. Чтобы строи...

🎥 Week 8 (part c) CS294-158 Deep Unsupervised Learning (4/3/19) -- Ilya Sutskever
👁 1 раз ⏳ 2928 сек.
UC Berkeley CS294-158 Deep Unsupervised Learning (Spring 2019)
Instructors: Pieter Abbeel, Xi (Peter) Chen, Jonathan Ho, Aravind Srinivas
https://sites.google.com/view/berkele...
Week 8c Lecture Contents:
- Ilya Sutskever guest lecture on GPT-2

​Основы Natural Language Processing для текста

🔗 Основы Natural Language Processing для текста
Обработка естественного языка сейчас не используются разве что в совсем консервативных отраслях. В большинстве технологических решений распознавание и обработка...

​Вышел ML.NET 1.0 RC. Что нового?

🔗 Вышел ML.NET 1.0 RC. Что нового?
ML.NET — это кроссплатформенная среда машинного обучения с открытым исходным кодом (Windows, Linux, macOS) для разработчиков .NET. Работая с ML.NET, разработчики...

Зачем нужен нейрон смещения

🎥 Нейронная сеть. Часть 4 . Нейрон смещения.
👁 31 раз ⏳ 345 сек.
Делюсь своим пониманием, для чего нужен нейрон смещения

Моя группа ВКонтакте https://vk.com/electronics_nn
Мой кошелёк на яндекс-деньги для желающ...

​Mathematical programming — a key habit to built up for advancing in data science

🔗 Mathematical programming — a key habit to built up for advancing in data science
We show a small step towards building the habit of mathematical programming, a key skill in the repertoire of a budding data scientist.

​Generating Images with Autoencoders

🔗 Generating Images with Autoencoders
In the following weeks, I will post a series of tutorials giving comprehensive introductions into unsupervised and self-supervised…

​Laurent Picard - Building smarter apps with Machine Learning, from magic to reality

🔗 Laurent Picard - Building smarter apps with Machine Learning, from magic to reality
Any sufficiently advanced technology is indistinguishable from magic (Arthur C Clarke). Well, Machine Learning can look like magic to most of us, but you don...

🎥 Applied Machine Learning 2019 - Lecture 20 - Neural Networks
👁 1 раз ⏳ 4002 сек.
Introduction to neural networks
Autograd
GPU acceleration
Deep learning frameworks

🎥 Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 6 - CNNs and Deep Q Learning
👁 1 раз ⏳ 4771 сек.
Professor Emma Brunskill, Stanford University
http://onlinehub.stanford.edu/

Professor Emma Brunskill
Assistant Professor, Computer Science
Stanford AI for Human Impact Lab
Stanford Artificial Intelligence Lab
Statistical Machine Learning Group

To follow along with the course schedule and syllabus, visit: http://web.stanford.edu/class/cs234/index.html

To get the latest news on Stanford’s upcoming professional programs in Artificial Intelligence, visit: http://learn.stanford.edu/AI.html

To view a

🎥 Машинное обучение в Яндексе
👁 2 раз ⏳ 4885 сек.
Александр Крайнов, Руководитель лаборатории машинного интеллекта компании "Яндекс"

​https://arxiv.org/abs/1903.08855

🔗 Linguistic Knowledge and Transferability of Contextual Representations
Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic knowledge they capture, we study the representations produced by several recent pretrained contextualizers (variants of ELMo, the OpenAI transformer language model, and BERT) with a suite of sixteen diverse probing tasks. We find that linear models trained on top of frozen contextual representations are competitive with state-of-the-art task-specific models in many cases, but fail on tasks requiring fine-grained linguistic knowledge (e.g., conjunct identification). To investigate the transferability of contextual word representations, we quantify differences in the transferability of individual layers within contextualizers, especially between recurrent neural networks (RNNs) and transformers. For instance, higher layers of RNNs are more task-specific, while transformer layers do not exhibit the same monotonic trend. In addition, to better understand what makes contextual word representations transferable, we compare language model pretraining with eleven supervised pretraining tasks. For any given task, pretraining on a closely related task yields better performance than language model pretraining (which is better on average) when the pretraining dataset is fixed. However, language model pretraining on more data gives the best results.

​https://arxiv.org/abs/1904.06236

🔗 Multimodal Machine Learning-based Knee Osteoarthritis Progression Prediction from Plain Radiographs and Clinical Data
Knee osteoarthritis (OA) is the most common musculoskeletal disease without a cure, and current treatment options are limited to symptomatic relief. Prediction of OA progression is a very challenging and timely issue, and it could, if resolved, accelerate the disease modifying drug development and ultimately help to prevent millions of total joint replacement surgeries performed annually. Here, we present a multi-modal machine learning-based OA progression prediction model that utilizes raw radiographic data, clinical examination results and previous medical history of the patient. We validated this approach on an independent test set of 3,918 knee images from 2,129 subjects. Our method yielded area under the ROC curve (AUC) of 0.79 (0.78-0.81) and Average Precision (AP) of 0.68 (0.66-0.70). In contrast, a reference approach, based on logistic regression, yielded AUC of 0.75 (0.74-0.77) and AP of 0.62 (0.60-0.64). The proposed method could significantly improve the subject selection process for OA drug-development trials and help the development of personalized therapeutic plans.

​OpenAI GPT-2: An Almost Too Good Text Generator

🔗 OpenAI GPT-2: An Almost Too Good Text Generator
❤️ Support the show and pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers 📝 The paper "Better Language Models and Their Implica...

​https://sites.google.com/view/deep-rl-bootcamp/lectures?fbclid=IwAR1jzH8D2adWGrAz2vQcz9N2gEh_BbIeckyWsLZZdFEEBmVYXmvi1Fnxl2c

🔗 Deep RL Bootcamp - Lectures

🎥 Arm A64fx and Post-K: Game-Changing CPU & Supercomputer for HPC
👁 1 раз ⏳ 1891 сек.
In this video from the HPC User Forum, Satoshi Matsuoka from RIKEN presents: Arm A64fx and Post-K: Game-Changing CPU & Supercomputer for HPC and its Convergence with Big Data / AI.

"With rapid rise and increase of Big Data and AI as a new breed of high-performance workloads on supercomputers, we need to accommodate them at scale, and thus the need for R&D for HW and SW Infrastructures where traditional simulation-based HPC and BD/AI would converge, in a BYTES-oriented fashion. Post-K is the flagship next

🎥 Face Recogntion with OpenCV and Deep Learning in Python
👁 1 раз ⏳ 2446 сек.
#face_recognition #deeplearning #python
In this new session, we are going to learn how to perform face recognition in both images and video streams using: OpenCV, Python, and Deep Learning.

We’ll start with a brief discussion of how deep learning-based facial recognition works, including the concept of “deep metric learning”. From there, I will help you install the libraries you need to actually perform face recognition. Finally, we’ll implement face recognition for both still images and video streams.

To

🎥 Introduction to Tensorflow 2.0 | Tensorflow 2.0 Features and Changes | Edureka
👁 1 раз ⏳ 831 сек.
***AI and Deep Learning with TensorFlow - https://www.edureka.co/ai-deep-learning-with-tensorflow ***
This video will provide you with a short and summarized knowledge of tensorflow 2.0 alpha, what all changes have been made and how is it better from the previous version.

--------------------------------------------------

About the course:

Edureka's Deep Learning in TensorFlow with Python Certification Training is curated by industry professionals as per the industry requirements & demands. You will mas