​Обучение с подкреплением или эволюционные стратегии? — И то, и другое

🔗 Обучение с подкреплением или эволюционные стратегии? — И то, и другое
Привет, Хабр! Мы нечасто решаемся размещать здесь переводы текстов двухлетней давности, без кода и явно академической направленности — но сегодня сделаем исключ...

🎥 Deep Learning House Price Prediction
👁 1 раз ⏳ 2031 сек.
Predict House Median Price

Please Subscribe !

►Get the code here:
https://github.com/randerson112358/Python/blob/master/Neural_Networks/Neural_Networks.ipynb

►Google Site:
https://colab.research.google.com/notebooks/welcome.ipynb

►Machine Learning Articles:
(1) Predicting House Prices:
https://medium.com/p/predict-boston-house-prices-using-python-linear-regression-90469e0a341

(2)Decision Tree Classifier:
https://medium.com/p/python-decision-tree-classifier-example-d73bc3aeca6

(3) Doing ML Without Code

​Get Started with PyTorch
An open source deep learning platform that provides a seamless path from research prototyping to production deployment.
https://pytorch.org/get-started/locally/

🔗 PyTorch
An open source deep learning platform that provides a seamless path from research prototyping to production deployment.

🎥 Machine Learning Infrastructure || Alexandra Johnson
👁 1 раз ⏳ 2605 сек.
Hyperparameter optimization (HPO) is a valuable tool for improving model performance, but it requires a lot of computational power -- so much that HPO experiments are often run on remote clusters. A requirement that data scientists become infrastructure experts just to manage model tuning infrastructure isn't feasible, so data science teams are turning to a variety of tools to help bridge the gap between the model builders and the infrastructure. This talk will provide an overview of machine learning infras

​Data Science и конференция в тропиках

Статьи про компьютерное зрение, интерпретируемость, NLP – мы побывали на конференции AISTATS в Японии и хотим поделиться обзором статей. Это крупная конференция по статистике и машинному обучению, и в этом году она проходит на Окинаве – острове недалеко от Тайваня. В этом посте Юлия Антохина (Yulia_chan) подготовила описание ярких статей из основной секции, в следующем вместе с Анной Папета расскажет про доклады приглашенных лекторов и теоретические исследования. Немного расскажем и про то, как проходила сама конференция и про “неяпонскую” Японию.

🔗 Data Science и конференция в тропиках
Статьи про компьютерное зрение, интерпретируемость, NLP – мы побывали на конференции AISTATS в Японии и хотим поделиться обзором статей. Это крупная конференция...

​Машинное обучение агентов в Unity

🔗 Машинное обучение агентов в Unity
Эта статья об агентах машинного обучения в Unity написана Майклом Лэнхемом — техническим новатором, активным разработчиком под Unity, консультантом, менеджером...

​Toward artificial intelligence that learns to write code

🔗 Toward artificial intelligence that learns to write code
Researchers combine deep learning and symbolic reasoning for a more flexible way of teaching computers to program.

​Mathematical Foundations of Data Science and Machine Learning (ML): Linear Algebra I: Vector Spaces

🔗 Mathematical Foundations of Data Science and Machine Learning (ML): Linear Algebra I: Vector Spaces
In data science, machine learning (ML), and artificial intelligence (AI), we usually deal not with single numbers but with multivariate (i.e. containing mult...

​Machine Learning: Recurrent Neural Networks And Long Short Term Memory (LSTM) Python Keras Example

🔗 Machine Learning: Recurrent Neural Networks And Long Short Term Memory (LSTM) Python Keras Example
In this video, we go over recurrent neural networks and LSTM networks. We perform sentiment analysis using keras. CONNECT Site: https://coryjmaklin.com/ Medi...

​Machine Learning Beginner Course: Neural Networks from scratch Part 2| AI Sciences Academy

🔗 Machine Learning Beginner Course: Neural Networks from scratch Part 2| AI Sciences Academy
This Course is developed by AI SCIENCES ACADEMY AI SCIENCES provides free courses and tutorials in Data Science, Machine Learning and AI for beginners like y...

​TD3: Learning To Run With AI

🔗 TD3: Learning To Run With AI
Learn to build one of the most powerful and state of the art algorithms in Reinforcement Learning, TD3

​DeepMind Made a Math Test For Neural Networks

🔗 DeepMind Made a Math Test For Neural Networks
📝 The paper "Analysing Mathematical Reasoning Abilities of Neural Models" is available here: https://arxiv.org/abs/1904.01557 ❤️ 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, Bruno Brito, Bryan Learn, Christian Ahlin, Christoph Jadanowski, Claudio Fernandes, Daniel Hasegan, Dennis Abts, Eri

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data

https://towardsdatascience.com/how-to-run-jupyter-notebooks-in-the-cloud-6ba14ca164da?source=collection_home---4------3-----------------------

🔗 How To Run Jupyter Notebooks in the Cloud
Focusing on data science instead of DevOps

​Как мы разрабатываем персональные товарные рекомендации

Наши клиенты-магазины хотят делать крутой маркетинг. Чтобы люди больше покупали, они регулярно шлют им email-рассылки. И каждый раз думают: “Что же написать в письме?”.

Можно писать просто: “Покупайте у нас почаще!”, но это не очень-то работает. Идея получше — вставлять в письмо рекламу товаров. Желательно, рекламу товаров, которые заинтересуют покупателей.

Дальше расскажу о том, как мы с нуля делали настоящие персональные рекомендации.
https://habr.com/ru/company/mindbox/blog/456082/

🔗 Как мы разрабатываем персональные товарные рекомендации
Наши клиенты-магазины хотят делать крутой маркетинг. Чтобы люди больше покупали, они регулярно шлют им email-рассылки. И каждый раз думают: “Что же написать в п...

This AI Makes Amazing DeepFakes…and More
https://youtu.be/aJq6ygTWdao

🎥 This AI Makes Amazing DeepFakes…and More
👁 6 раз ⏳ 289 сек.
Check out Lambda Labs here: https://lambdalabs.com/papers

📝 The paper "Deferred Neural Rendering: Image Synthesis using Neural Textures" is available here:
https://niessnerlab.org/projects/thies2019neural.html

My earlier work on neural rendering in the first part of the video is available here:
https://users.cg.tuwien.ac.at/zsolnai/gfx/gaussian-material-synthesis/

🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
313V, Alex Haro, Andrew Melnychuk, Angelos Evrip

​10 Simple hacks to speed up your Data Analysis in Python

🔗 10 Simple hacks to speed up your Data Analysis in Python
Tips and Tricks, especially in the programming world, can be very useful. Sometimes a little hack can be both time and life-saving. A…

Top 5 free Handbooks for Datascience professionals:

If you don't have time or capacity to read many books📚 make sure at least you cover these 5 absolute essentials:

✅"Python Data Science Handbook: ESSENTIAL TOOLS FOR WORKING WITH DATA" by Jake VanderPlas -This book covers Numpy, data manipulation with Pandas, visualization methods, and Machine Learning. https://lnkd.in/gxcW3Ku

✅"MACHINELEARNING YEARNING" by Andrew Ng Includes: -Prioritize the most promising directions for an AI project -Diagnose errors in a machine learning system -Build ML in complex settings, such as mismatched training/test sets -Set up an ML project to compare to and/or surpass human-level performance -Know when and how to apply end-to-end learning, transfer learning, and multi-task learning https://lnkd.in/g_D8pwi

✅"The DeepLearning textbook" by Ian Goodfellow and Yoshua Bengio and Aaron Courville https://lnkd.in/gfBv4h5

✅"The Hundred-Page MachineLearning Book" by Andriy Burkov -All you need to know about Machine Learning in a hundred pages. https://lnkd.in/gNb22Qh

✅"The DataEngineering Cookbook Mastering The Plumbing Of Data Science" by Andreas Kretz 👇

📝 The Data Engineering Cookbook-1.pdf - 💾3 425 076

🎥 Chao Han: Deep Learning vs. Conventional Machine Learning | PyData Miami 2019
👁 1 раз ⏳ 2313 сек.
Over the past few years, deep learning has given rise to a massive collection of ideas and techniques which are disruptive to conventional machine learning practices. However, are those ideas totally different from the traditional methods? Where are the connections and differences? What are the advantages and disadvantages? How practical are the deep learning methods for business applications? Chao will share her thoughts on those questions based on her readings and hands on experiments in the areas of text