​3 ловушки, в которые попадают начинающие Data Scientist

🔗 3 ловушки, в которые попадают начинающие Data Scientist
Вот что может случиться, если плохо знаешь математику. Привет! Это Петр Лукьянченко, автор и руководитель онлайн-курсов «Математика для Data Science» в OTUS.

🎥 A Spatiotemporal Epidemic Model to Quantify the Effects of Contact Tracing, Testing, and Containment
👁 1 раз ⏳ 2430 сек.
Motivated by the current COVID-19 outbreak, we introduce a novel epidemic model based on marked temporal point processes that is specifically designed to make fine-grained spatiotemporal predictions about the course of the disease in a population. Our model can make use and benefit from data gathered by a variety of contact tracing technologies and it can quantify the effects that different testing and tracing strategies, social distancing measures, and business restrictions may have on the course of the di

​Scaling up real-time inference with online regression and more

🔗 Scaling up real-time inference with online regression and more
Value of regression for decision making, how to scale it to massive data in realtime, and paving the way for other exciting methods.

​Identifying Statistical Bias in Dataset Replication

🔗 Identifying Statistical Bias in Dataset Replication
Research highlights and perspectives on machine learning and optimization from MadryLab.

​Google Says It Will Not Build Custom A.I. for Oil and Gas Extraction

🔗 Google Says It Will Not Build Custom A.I. for Oil and Gas Extraction
A Greenpeace report details Silicon Valley’s ties to Big Oil — and spurs Google to take a step towards opting out

🎥 Infrastructure for Machine Learning by Natalie Pistunovich
👁 1 раз ⏳ 2919 сек.
During our April Talks we have Natalie talking about Machine Learning!


TensorFlow 2.0 is the new version of the end-to-end open-source platform for Machine Learning, where researchers can push the state-of-the-art in ML and developers can build and deploy ML and AI powered intermediate applications. But the ML code, that is at the heart of an ML system in production, usually accounts for a few percents of the entire codebase. In this talk, Natalie will share from her experience the infrastructure side of

🎥 Deep Neural Networks for Structured Prediction
👁 1 раз ⏳ 3817 сек.
2020-03-05

Abstract:
Recent advances in deep neural networks (DNNs) have revolutionized fields such as natural language processing, computer vision, and robotics, while also recently impacting other fields such as biology, computational mechanics, and health care. Many of the problems appearing in these domains are structured prediction tasks, which involve predicting multiple output variables whose correlations jointly form a structure (e.g., a set, sequence, tree, or arbitrary graph). Classically, thes

🎥 Розничная торговля и технологии в период кризиса
👁 3 раз ⏳ 3778 сек.
Как алгоритмы машинного обучения помогают ретейлерам решать, какие именно продукты попадут на полки магазинов и сколько они будут стоить? Могли ли нейросети предсказать недавний ажиотаж на гречку и консервы? Почему неправильный прогноз может привести к потере клиентов и как этого избежать? Об этом и о том, изменилась ли отрасль розничной торговли из-за пандемии, рассказал Валерий Бабушкин, директор по моделированию и анализу данных X5 Retail Group, в беседе с Анастасией Баскаковой, заместителем заведующего

​Evolution of Language Models: N-Grams, Word Embeddings, Attention & Transformers

🔗 Evolution of Language Models: N-Grams, Word Embeddings, Attention & Transformers
This post collates research on the advancements of Natural Language Processing (NLP) over the years.

​Probability and Statistics for Data Science (2019)
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Открыть в Telegram



📝 Probability_and_statistics_for_data_science_math_+_R_+_data_by_Matloff.pdf - 💾6 624 896

​Identify objects moving on a conveyor belt using Opencv with Python - Pysource

🔗 Identify objects moving on a conveyor belt using Opencv with Python - Pysource
In this tutorial we will learn how to create a simple prototype to detect objects passing on a conveyor belt. We will use exagonal nuts as objects. I have two sizes, a small one and a bigger one. If the small nuts are detected the...

​Примеры технического долга при внедрении BI-систем

🔗 Примеры технического долга при внедрении BI-систем
Разработка и развертывание систем BI достаточно быстрый и дешевый процесс, но их обслуживание с течением времени является дорогостоящим. Это можно представить, ч...

​Teaching from Home - Quick Start Guide

By Andrew Ng

Many of us are working to quickly transition from teaching in a live classroom to teaching online
from home. The goal of this document is to help you make that transition quickly and
successfully with a minimum amount of complexity. We will go over the basics, and only the
basics here.
@ArtificialIntelligenceArticles

https://drive.google.com/file/d/1ZPUQTKxkMLPxinT4SHU3_k_p4_Scnqgv/view

🔗 Andrew Ng - Teaching from home - Quick Start guide.pdf

​Основы Data Vault

🔗 Основы Data Vault
В настоящее время, в сфере анализа данных и BI, уже не возможно не встретить такое понятия как DATA VAULT. Однако, на мой взгляд, есть некоторый недостаток инфор...

​The mathematical foundations of probability

🔗 The mathematical foundations of probability
A measure-theoretic introduction

​TD Learning — Solving the evaluation problem

🔗 TD Learning — Solving the evaluation problem
In the last blog post, we’ve talked about how Monte Carlo can solve the evaluation problem for a model-free environment.

🎥 Machine Learning Foundations: Ep #5 - Classifying real-world images
👁 1 раз ⏳ 1054 сек.
Machine Learning Foundations is a free training course where you’ll learn the fundamentals of building machine learned models using TensorFlow.

In Episode 5 we’ll look at how to use Convolutional Neural Networks to classify complex features, with a hands-on example to tackle a more challenging computer vision problem--classifying images of horses and humans!

Exercise 3 answer → https://goo.gle/3dml4e3
Example: Classifying complex images → https://goo.gle/2YLupZ7
Exercise 4 → https://goo.gle/2WbPo5E

Tenso

🎥 Tutorial: Biomedical Image Reconstruction—From Foundations To Deep Neural Networks, ICASSP 2020
👁 1 раз ⏳ 9534 сек.
Thanks to Prof. Michael Unser, CIBM Signal Processing Mathematical Imaging Section Head, and Dr. Pol del Aguila Pla, CIBM research staff, learn about Biomedical Image Reconstruction in this three part tutorial:
Part I: Imaging as an inverse problem and classical image reconstruction
Part II: Sparsity-based image reconstruction
Part III: The (deep) learning (r)evolution

Tutorial Summary :
Biomedical imaging plays a key role in medicine and biology. Its range of applications and its impact in research and

​Announcing the 7th Fine-Grained Visual Categorization Workshop">
Announcing the 7th Fine-Grained Visual Categorization Workshop

🔗 Announcing the 7th Fine-Grained Visual Categorization Workshop
Posted by Christine Kaeser-Chen, Software Engineer and Serge Belongie, Visiting Faculty, Google Research Fine-grained visual categorizat...

​Заголовок этой статье придумал компьютер

🔗 Заголовок этой статье придумал компьютер
И это правда, но всё по порядку. Пока развитие искусственного интеллекта идет, не убоюсь этого слова, однобоко — по конкретным задачам и в узких областях. Никто...