Channel Public Channel

Data Place

@dataplace

Канал про данные, науку о данных и про обучение работе с данными.
Автор: Ирина Радченко, доцент, канд. техн. наук, любитель данных и Computer Science, в Телеграме -- @dadaistka

Open in Telegram

Subscribers: 524
Photos: 38
Videos: 0
Links: 219

Showing posts older than #51 · Back to latest

Older Posts 20 shown

Post #50 145 May 26, 2018, 07:23 UTC

https://hackernoon.com/how-to-build-a-simple-spam-detecting-machine-learning-classifier-4471fe6b816e

Hackernoon HackerNoon - read, write and learn about any technology How hackers start their afternoon. HackerNoon is a free platform with 25k+ contributing writers. 100M+ humans have visited HackerNoon to learn about technology

Post #49 138 May 26, 2018, 07:22 UTC

Forwarded from Владислав

Еще могут быть полезны ресурсы: leetcode.com, hackerrank.com, codeforces.com, для практики.

Post #48 130 May 26, 2018, 07:21 UTC

Forwarded from Владислав

https://www.coursera.org/specializations/algorithms
https://www.coursera.org/specializations/data-structures-algorithms
https://www.coursera.org/learn/algorithms-part1

https://openedu.ru/course/ITMOUniversity/PADS/

https://stepik.org/course/217/syllabus
https://stepik.org/course/1547/syllabus
https://stepik.org/course/579/syllabus

Post #47 124 May 26, 2018, 07:21 UTC

Полезные ссылки на онлайн-курсы по алгоритмам.

Post #45 145 May 21, 2018, 17:14 UTC

Очень интересная и полезная книга по глубокому обучению (Deep Learning. A Practitioner's Approach).
В ней также рассматривается библиотека Deeplearning4j (DL4J) и DataVec.
В издательстве ДМК вышел ее перевод на русском языке.
В русском переводе она называется "Глубокое обучение с точки зрения практика".

Post #44 6 May 21, 2018, 08:58 UTC

Forwarded from Machinelearning

https://machinelearningmastery.com/how-to-transform-data-to-fit-the-normal-distribution/

MachineLearningMastery.com How to Transform Data to Better Fit The Normal Distribution - MachineLearningMastery.com A large portion of the field of statistics is concerned with methods that assume a Gaussian distribution: the familiar bell curve. If your data has a Gaussian distribution, the parametric methods are powerful and well understood. This gives some incentive…

Post #43 170 May 20, 2018, 15:35 UTC

Список питоновских библиотек для обработки естественного языка.

https://kleiber.me/blog/2018/02/25/top-10-python-nlp-libraries-2018/

kleiber.me - Ingo Kleiber Top 10 Python Libraries for Natural Language Processing (2018) There are various Python libraries for natural language processing (NLP). This article discusses ten of the most important Python libraries and modules for analyzing language computationally.

Post #41 134 May 20, 2018, 11:44 UTC

Библиотека Keras – А. Джулли, С. Пал (ru) 2017

Краткое, но обстоятельное введение в современные нейронные сети, искусственный интеллект и технологии глубокого обучения.

Post #40 147 May 19, 2018, 10:58 UTC

Краткий обзор 10 популярных алгоритмов машинного обучения для новичков (A Tour of The Top 10 Algorithms for Machine Learning Newbies):https://towardsdatascience.com/a-tour-of-the-top-10-algorithms-for-machine-learning-newbies-dde4edffae11

Towards Data Science Your home for data science and AI. The world’s leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals.

Post #39 133 May 19, 2018, 10:55 UTC

Пара статей Deep Learning With Apache Spark от Favio Vázquez.
1. https://towardsdatascience.com/deep-learning-with-apache-spark-part-1-6d397c16abd
2. https://towardsdatascience.com/deep-learning-with-apache-spark-part-2-2a2938a36d35

Medium Deep Learning With Apache Spark — Part 1 First part on a full discussion on how to do Distributed Deep Learning with Apache Spark. This part: What is Spark, basics on Spark+DL and…

Post #38 136 May 18, 2018, 07:27 UTC

Полезные ссылки по библиотекам визуализации на Питоне.
1. HoloViews 1.10 Release: http://blog.pyviz.org/release_1.10.html
2. GeoViews 1.5 Release: http://blog.pyviz.org/release_1.5.html
3. Bokeh: https://bokeh.pydata.org/en/latest/
4. Plotly: https://plot.ly/python/
5. VisPy: http://vispy.org/gallery.html

Больше ссылок на библиотеки можно посмотреть в моем блоге на Medium: https://medium.com/@iradche/python-and-data-visualization-3ad94a9f313c

Bokeh Bokeh documentation Bokeh is a Python library for creating interactive visualizations for modern web browsers. It helps you build beautiful graphics, ranging from simple plots to complex dashboards with streaming data...

Post #37 146 May 17, 2018, 10:01 UTC

Machine Learning Yearning от Andrew Ng: https://gallery.mailchimp.com/dc3a7ef4d750c0abfc19202a3/files/aacac1fd-b6bf-4ddc-9571-c9f1054891b6/Ng_MLY05.pdf

Post #36 151 May 17, 2018, 10:00 UTC

https://habr.com/company/piter/blog/354912/

Хабр Экскурсия по PyTorch Привет, Хабр! Еще до конца мая у нас выйдет перевод книги Франсуа Шолле "Глубокое обучение на Python" (примеры с использованием библиотек Keras и Tensorflow).

Post #35 179 May 13, 2018, 14:01 UTC

Список с полезными ссылками по теме CRISP-DM (версия 1, 13 мая 2018 г.):

https://medium.com/@iradche/crisp-dm-cross-industry-standard-process-for-data-mining-45e1756483cd

Medium CRISP-DM (Cross-industry standard process for data mining) Cross-industry standard process for data mining, known as CRISP-DM, is an open standard process model that describes common approaches used…

Post #34 7 May 9, 2018, 08:21 UTC

Forwarded from Machinelearning

https://machinelearningmastery.com/statistics-books-for-machine-learning/

Post #33 167 May 9, 2018, 08:15 UTC

https://techcrunch.com/2018/05/08/google-announces-a-new-generation-for-its-tpu-machine-learning-hardware/

TechCrunch Google announces a new generation for its TPU machine learning hardware As the war for creating customized AI hardware heats up, Google announced at Google I/O 2018 that is rolling out out its third generation of silicon, the Tensor Processor Unit 3.0. Google CEO Sundar Pichai said the new TPU pod is eight times more powerful…

Post #32 7 Apr 30, 2018, 15:48 UTC

Forwarded from ∏ρØƒuñçτØρ Øπτµç∑ | 👁‍🗨››››

Post #31 213 Apr 17, 2018, 09:33 UTC

Интервью (с транскриптом) с Nathan Marz о лямбда-архитектуре: https://www.infoq.com/interviews/marz-lambda-architecture

Его же книга Big Data: Principles and best practices of scalable realtime data systems: https://www.goodreads.com/book/show/13421400-big-data

InfoQ Nathan Marz on Storm, Immutability in the Lambda Architecture, Clojure Nathan Marz explains the ideas behind the Lambda Architecture and how it combines the strengths of both batch and realtime processing as well as immutability. Also: Storm, Clojure, and much more.

Post #30 194 Apr 16, 2018, 22:57 UTC

Схема Spark (взято из DataCamp)

Post #29 172 Apr 15, 2018, 18:47 UTC

Время заняться PySpark-ом: http://spark.apache.org/docs/2.1.0/api/python/pyspark.html

PySpark Cheat Sheet: Spark in Python:
https://www.datacamp.com/community/blog/pyspark-cheat-sheet-python

Еще парочка полезных ссылок по PySpark:
1. https://blog.sicara.com/get-started-pyspark-jupyter-guide-tutorial-ae2fe84f594f
2. https://www.tutorialspoint.com/pyspark/index.htm

Datacamp PySpark Cheat Sheet: Spark in Python This PySpark cheat sheet with code samples covers the basics like initializing Spark in Python, loading data, sorting, and repartitioning.

Older posts →