🎥 Machine Learning and JavaScript - City JS Conf 2019
👁 1 раз ⏳ 1911 сек.
Elle Haproff

JavaScript probably isn't the first language which springs to mind when you say 'machine learning', but that does seem to be changing, especially with the release of TensorFlow.js last year.

This talk gives a high level overview of what machine learning and neural networks are, shows how to get started with TensorFlow.js, and demos a number of projects which use JavaScript and AI.

_

About Pusher Sessions:

We're bringing the meetup to you. With Sessions, you can watch recordings of top-not

🎥 Data Science Tutorial | Data Science Courses | Learning Data Science Online | Intellipaat
👁 2 раз ⏳ 33731 сек.
Intellipaat Data Science Course:- https://intellipaat.com/data-scientist-course-training/
In this complete Data Science tutorial you will learn data science online all the major concepts to become a data scientist. You will learn concepts like what is data science, supervised learning concepts like data manipulation, data visualization, linear regression, logistic regression, decision tree, random forest, unsupervised learning concepts like k means clustering, user based & item based filtering, association

🎥 Возможности Python для анализа данных и моделирования
👁 1 раз ⏳ 2674 сек.
Конференция AI разработчиков 27 апреля 2019.
Спикер: Полина Полунина (практикующий Data Scientist, X5 Retail Group. Победитель и призер международных чемпионатов по машинному обучению, предикативному финансово-математическому моделированию)

🎥 Using events based data architecture for near real time, machine learning / Nir Malbin
👁 1 раз ⏳ 2017 сек.
HighLoad++ Siberia

24 и 25 июня 2019
Новосибирск

Подробности и билеты по ссылке https://www.highload.ru/siberia/2019

--------
HighLoad++ Moscow 2018

Зал «Москва»
9 ноября, 12:00

Тезисы и презентация:
http://www.highload.ru/moscow/2018/abstracts/4310

Gett is using events based data architecture, collecting millions of records per minute. In this talk i shall describe how we built, using this data, an end-to-end machine learning solution for predicting the company KPI's in near real time.
--------
Н

​timsainb/tensorflow2-generative-models

🔗 timsainb/tensorflow2-generative-models
Implementations of a number of generative models in Tensorflow 2. GAN, VAE, Seq2Seq, VAEGAN, GAIA, Spectrogram Inversion. Everything is self contained in a jupyter notebook for easy export to colab...

​How to Use Transfer Learning when Developing Convolutional Neural Network Models

🔗 How to Use Transfer Learning when Developing Convolutional Neural Network Models
Deep convolutional neural network models may take days or even weeks to train on very large datasets. A way to short-cut this process is to re-use the model weights from pre-trained models that were developed for standard computer vision benchmark datasets, such as the ImageNet image recognition tasks. Top performing models can be downloaded and …

​ICLR 2019: Overcoming limited data

🔗 ICLR 2019: Overcoming limited data
Deep learning has proven powerful at many tasks, but requires massive amounts of data. However a number of new techniques are emerging

​Uber datasets in BigQuery: Driving times around SF and your city too

🔗 Uber datasets in BigQuery: Driving times around SF and your city too
Uber keeps adding new cities to their public data program — and here I’ll show you how to load this data into BigQuery. We’ll be able to…

🎥 Unsupervised machine translation
👁 1 раз ⏳ 3403 сек.
Main topics:
Unsupervised dictionary induction
Unsupervised neural machine translation
Unsupervised phrase based machine translation


Presentation: https://docs.google.com/presentation/d/1iwi2i4gaBZqlFQE6dkeHfzXgQWFG9pJlsEfcUTkC5aA/edit?usp=sharing

Latest course updates and insights: https://xn--r1a.website/dlinnlp


Vladislav Lyalin, iPavlov

​Scalable Python Code with Pandas UDFs: A Data Science Application

🔗 Scalable Python Code with Pandas UDFs: A Data Science Application
Making Python code run at massive scale in the cloud

🎥 Machine learning в JavaScript. Библиотеки и решения
👁 1 раз ⏳ 2177 сек.
Максим Северухин [Малый лекторий]

🎥 Episode 60: Predicting your mouse click (and a crash course in deeplearning)
👁 1 раз ⏳ 2393 сек.
Source:
https://www.podbean.com/media/share/pb-xy6qt-b1516a

Deep learning is the future. Get a crash course on deep learning. Now! In this episode I speak to Oliver Zeigermann, author of Deep Learning Crash Course published by Manning Publications at https://www.manning.com/livevideo/deep-learning-crash-course
Oliver (Twitter: @DJCordhose) is a veteran of neural networks and machine learning. In addition to the course - that teaches you concepts from prototype to production - he's working on a really cool

🎥 Intel® AVX512 Deep Learning Boost: Intrinsic Functions | AI News | Intel Software
👁 1 раз ⏳ 72 сек.
Learn about a deep learning code sample that you can use to take advantage of the new Intel® AVX-512-Deep Learning Boost!

Find detailed descriptions of Intel® AVX-512 intrinsics: https://intel.ly/2YvJr1u

Read “Code Sample: Intel® AVX512-Deep Learning Boost: Intrinsic Functions”: https://intel.ly/2Yx6vwN

Subscribe to the Intel Software YouTube Channel: http://bit.ly/2iZTCsz

AI News YouTube Playlist: https://intel.ly/2ONz0W0

About Intel Software:
The Intel® Developer Zone encourages and supports software

🎥 32. ImageNet is a Convolutional Neural Network (CNN), The Convolution Rule
👁 1 раз ⏳ 2839 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

Professor Strang begins the lecture talking about ImageNet, a large visual database used in visual object recognition software research. ImageNet is an example of a convolutional neural network (CNN). The rest of the lecture focuses on conv

🎥 26. Structure of Neural Nets for Deep Learning
👁 1 раз ⏳ 3197 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 is about the central structure of deep neural networks, which are a major force in machine learning. The aim is to find the function that's constructed to learn the training data and then apply it to the test data.

License: Cr

​The Power of Visualization in Data Science

🔗 The Power of Visualization in Data Science
A picture really does say a thousand words.

🎥 Building our first Convolutional Neural Networks in TensorFlow step by step
👁 1 раз ⏳ 1067 сек.
In the previous tutorial, we built Deep Neural Networks using TensorFlow. Most practical applications of deep learning today are built using programming frameworks, which have many built-in functions you can simply call.

In this notebook, we will:
- Implement helper functions that we will use when implementing a TensorFlow model
- Implement a fully functioning ConvNet using TensorFlow

After this tutorial we will be able to:
- Build and train a ConvNet in TensorFlow for a classification problem

Text versi

Attacking Machine Learning: On the Security and Privacy of Neural Networks
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

https://www.youtube.com/watch?v=3hig_oEz8Rg

🎥 Attacking Machine Learning: On the Security and Privacy of Neural Networks
👁 1 раз ⏳ 2907 сек.
Nicholas Carlini, Research Scientist, Google

Despite significant successes, machine learning has serious security and privacy concerns. This talk will examine two of these. First, how adversarial examples can be used to fool state-of-the-art vision classifiers (to, e.g., make self-driving cars incorrectly classify road signs). Second, how to extract private training data out of a trained neural network.Learning Objectives:1: Recognize the potential impact of adversarial examples for attacking neural networ

🎥 Deep Policy Gradient Algorithms: A Closer Look
👁 1 раз ⏳ 3279 сек.
Deep reinforcement learning methods are behind some of the most publicized recent results in machine learning. In spite of these successes, however, deep RL methods face a number of systemic issues: brittleness to small changes in hyperparameters, high reward variance across runs, and sensitivity to seemingly small algorithmic changes.

In this talk, we take a closer look at the potential root of these issues. Specifically, we study how the policy gradient primitives underlying popular deep RL algorithms re

🎥 Deep Learning skills for Product Development | by Vladimir Iglovikov | Kaggle Days SF
👁 1 раз ⏳ 2738 сек.
Vladimir Iglovikov
"Deep Learning skills for Product Development"

Presentation was held at Kaggle Days, San Francisco, a two day user conference for Kagglers and data scientists.

This edition is presented by LogicAI with sponsorship from Kaggle and Google Cloud.

About the presenter:
Vladimir got his Ph.D. in Theoretical Condensed Matter Physics at UC Davis. After graduation he was developing Energy Disaggregation algorithms that were a combination of the signal processing and machine learning techniques