A disciplined approach to neural network hyper-parameters

Recommendations on how to optimize learning rate, weight decay, momentum and batch size.

ArXiV: https://arxiv.org/pdf/1803.09820.pdf

​Data Science with Medium Story Stats in Python
A Python toolkit for data science with Medium article statistics

https://towardsdatascience.com/analyzing-medium-story-stats-with-python-24c6491a8ff0

🔗 Analyzing Medium Story Stats with Python – Towards Data Science
Data science with my Medium article statistics and simple Python tools you can use for yourself!

Load that &%$*# Checkpoint!
https://towardsdatascience.com/load-that-checkpoint-51142d44fb5d?source=collection_home---4------0---------------------

https://habr.com/post/434934/

Как масштабируется обучение искусственного интеллекта

#machinelearning #neuralnets #deeplearning #машинноеобучение

Наш телеграмм канал - https://t.me/ai_machinelearning_big_data

DeepMind’s Take on How To Create a Benign AI

🎥 DeepMind’s Take on How To Create a Benign AI
👁 1 раз ⏳ 255 сек.
The paper "Scalable agent alignment via reward modeling: a research direction" is available here:
1. https://arxiv.org/abs/1811.07871
2. https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84

Pick up cool perks on our Patreon page:
› https://www.patreon.com/TwoMinutePapers

We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
313V, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Christi

​Artwork Personalization at Netflix | Data Council NYC '18

🔗 Artwork Personalization at Netflix | Data Council NYC '18
ABOUT THE TALK: For many years, the main goal of the Netflix personalized recommendation system has been to get the right titles in front each of our members...

​Building a Modern Machine Learning Platform on Kubernetes | Data Council NYC '18

🔗 Building a Modern Machine Learning Platform on Kubernetes | Data Council NYC '18
ABOUT THE TALK: The last few years have been transformative for the state of machine learning and AI. This talk goes into details of the ML Platform. In this...

🎥 Машинное обучение с нуля миф или реальность
👁 57 раз ⏳ 1977 сек.
Тема: Машинное обучение с нуля: миф или реальность?

Спикер: Дмитрий Козлов. Computer Vision, Deep Learning engineer.

Дмитрий окончил математический факультет КемГУ и магистратуру ВМК МГУ. Работал в Parallels, Odin, Mati Biometrics, Imagemetry. Активный участник крупнейшего в России сообщества по машинному обучению Open Data Science.

Область профессиональных интересов: Machine learning, Computer Vision, Deep Learning

На видео Дмитрий рассказывает какой путь нужно пройти, чтобы стать специалистом в те

NLP 2018 Highlights
By Elvis Saravia.
Summary of all the biggest NLP stories, state-of-the-art results and new interesting research directions of the year coming from both academia and the industry

📝 NLP_2018_Highlights.pdf - 💾3 104 047

Data-science? Agile? Cycles? My method for managing data-science projects in the Hi-tech industry.
https://towardsdatascience.com/data-science-agile-cycles-my-method-for-managing-data-science-projects-in-the-hi-tech-industry-b289e8a72818?source=collection_home---4------1---------------------

https://habr.com/post/435066/

Graphcore привлекает $200 млн. от BMW, Microsoft и ведущих инвесторов, чтобы ускорить производство процессоров для ИИ

#machinelearning #neuralnets #deeplearning #машинноеобучение

Наш телеграмм канал - https://t.me/ai_machinelearning_big_data

🎥 Conversational UI: Say Hi to Dialogflow. Антон Валюх, DataArt
👁 1 раз ⏳ 5039 сек.
Язык доклада: русский.
Язык презентации: английский.

Senior Android - разработчик Антон Валюх на примере создания приложения для бронирования приема у врача показывает, как проектировать и создавать агенты с помощью инструмента Dialogflow.

Обсуждаем встроенный механизм машинного обучения. На примере интеграции с Google Assistant разберем примеры работы создаваемого приложения.

Антон Валюх, Senior Android Developer и Team Leader в DataArt. В IT-индустрии — девять лет, из них восемь пишет под Android. Сейч

​GRCon18 - Advances in Machine Learning for Sensing and Communications Systems

🔗 GRCon18 - Advances in Machine Learning for Sensing and Communications Systems
Slides available here: https://www.gnuradio.org/grcon/grcon18/presentations/advances_in_machine_learning_for_sensing_and_communications_systems/deepsig_grcon...

​How to Unleash the Power of IBM Machine Learning to Outthink Limits

🔗 How to Unleash the Power of IBM Machine Learning to Outthink Limits
SHARE St. Louis IBM Machine Learning enable your business to unlock and harness all insights from the data, without moving it around. Come and learn how to l...

​Machine Learning Engineer Jobs, Resume & Salary | Machine Learning Engineer Salary Report | Edureka

🔗 Machine Learning Engineer Jobs, Resume & Salary | Machine Learning Engineer Salary Report | Edureka
( Machine Learning Engineer Masters Program: https://www.edureka.co/masters-program/machine-learning-engineer-training ) This video will provide you with det...

​Top 10 IPython Notebook Tutorials for Data Science and Machine Learning

List mostly for beginners.

Link: https://www.kdnuggets.com/2016/04/top-10-ipython-nb-tutorials.html

#novice #beginner #ipython #jupyter

🔗 Top 10 IPython Notebook Tutorials for Data Science and Machine Learning

​How to Develop a Snapshot Ensemble Deep Learning Neural Network in Python With Keras

🔗 How to Develop a Snapshot Ensemble Deep Learning Neural Network in Python With Keras
Model ensembles can achieve lower generalization error than single models but are challenging to develop with deep learning neural networks given the computational cost of training each single model. An alternative is to train multiple model snapshots during a single training run and combine their predictions to make an ensemble prediction. A limitation of this …

​Finding the optimal dating strategy for 2018 with probability theory
How knowing some Statistical theory may make finding Mr. Right slightly easier?

https://towardsdatascience.com/probability-theory-and-the-optimal-dating-strategy-for-2018-2b75b26fb0b

🔗 Probability theory and the optimal dating strategy for 2018
How knowing some Statistical theory may make finding Mr. Right slightly easier?

🎥 AWS re:Invent 2018: Driving Machine Learning and Analytics Use Cases with AWS Storage (STG302)
👁 1 раз ⏳ 657 сек.
You’ve designed and built a well-architected data lake and ingested extreme amounts of structured and unstructured data. Now what? In this session, we explore real-world use cases where data scientists, developers, and researchers have discovered new and valuable ways to extract business insights using advanced analytics and machine learning. We review Amazon S3, Amazon Glacier, and Amazon EFS, the foundation for the analytics clusters and data engines. We also explore analytics tools and databases, includi