​MNIST-GAN: Detailed step by step explanation & implementation in code

https://medium.com/@garimanishad/mnist-gan-detailed-step-by-step-explanation-implementation-in-code-ecc93b22dc60

🔗 MNIST-GAN: Detailed step by step explanation & implementation in code
Don’t know anything about GAN? You’ve come to the right place!

Building a Recommender System Using Embeddings
At the core of the Drop ecosystem are two key entities: our members and our partner brands.

https://drop.engineering/building-a-recommender-system-using-embeddings-de5a30e655aa

​Как правильно готовить значки для GitHub

🔗 Как правильно готовить значки для GitHub
Написать эту статью, меня сподвиг факт появления значка на GitHub “Developed by Mad Devs”. Очень классная идея! И после того как попросил…

​Визуализация новостей рунета

Представьте себе, что вы поспорили с друганом, что было раньше — курица или яйцо повышение какого-то налога, к примеру, или новости на эту тему, или вовсе важное событие заглушили тучей новостей про новую песню, скажем, Киркорова. Удобно было бы посчитать, сколько новостей на каждую тему было в каждый конкретный момент времени, а потом наглядно это представить. Собственно, этим и занимается проект “радар новостей рунета”. Под катом мы расскажем, при чём здесь машинное обучение и как любой доброволец может в этом поучаствовать.
#DataMining
https://habr.com/ru/company/ods/blog/460287/
#Машинноеобучение

🔗 Визуализация новостей рунета
Представьте себе, что вы поспорили с друганом, что было раньше — курица или яйцо повышение какого-то налога, к примеру, или новости на эту тему, или вовсе важн...

#machinelearning #deeplearning #computervision
Explained - Neural Style Transfer Research Paper

🎥 Explained - Neural Style Transfer Research Paper
👁 1 раз ⏳ 776 сек.
#machinelearning #deeplearning #computervision #neuralnetworks #ai
Neural Style Transfer refers to a class of software algorithms that manipulate digital images, or videos, to adopt the appearance or visual style of another image. NST algorithms are characterized by their use of deep neural networks in order to perform the image transformation.

Subscribe and follow me on other platforms for more updates. I generally reply to messages on instagram.
Instagram- https://www.instagram.com/ayush._.chaurasia/

My

​Predicting Market Movement Using Machine Learning
When J.P. Morgan was asked what the market will do he responded in three simple words. “It will fluctuate.”
https://medium.com/@michaelemmert1234/predicting-market-movement-using-machine-learning-a87b6f8a6203?source=topic_page---------2------------------1

🔗 Predicting Market Movement Using Machine Learning
When J.P. Morgan was asked what the market will do he responded in three simple words. “It will fluctuate.” He has been proven correct…

Developing a brain atlas using deep learning with Theofanis Karayannis - TWIML Talk #287
https://www.youtube.com/watch?v=b7LgtIWt9i8

🎥 Developing a brain atlas using deep learning with Theofanis Karayannis - TWIML Talk #287
👁 1 раз ⏳ 2322 сек.
Today we’re joined by Theofanis Karayannis, Assistant Professor at the Brain Research Institute of the University of Zurich. Theo’s research is currently focused on understanding how circuits in the brain are formed during development and modified by experiences. Working with animal models, Theo segments and classifies the brain regions, then detects cellular signals that make connections throughout and between each region. How? The answer is (relatively) simple: Deep Learning. In this episode we discuss:

​Kaggle Live Coding: Hierarchical Document Clustering | Kaggle

🔗 Kaggle Live Coding: Hierarchical Document Clustering | Kaggle
Last week we successfully got clusters (yay!) but they could use some fine-tuning. This week we'll starting to look at hierarchical clusters and possibly work on some visualizations. You can find the code we've written so far here: https://www.kaggle.com/rtatman/forum-post-embeddings-clustering SUBSCRIBE: https://www.youtube.com/c/kaggle?sub_... About Kaggle: Kaggle is the world's largest community of data scientists. Join us to compete, collaborate, learn, and do your data science work. Kaggle's platform

​How and why I got 75Gb of free foreign exchange “Tick” data.
With full Python code to scrape, extract, transform and load it into a HDF5 data store to please your future self.

https://towardsdatascience.com/how-and-why-i-got-75gb-of-free-foreign-exchange-tick-data-9ca78f5fa26c?source=collection_home---4------2-----------------------

🔗 How and why I got 75Gb of free foreign exchange “Tick” data.
With full Python code to scrape, extract, transform and load it into a HDF5 data store to please your future self.

​An Example of Hyperparameter Optimization on XGBoost, LightGBM and CatBoost using Hyperopt

https://towardsdatascience.com/an-example-of-hyperparameter-optimization-on-xgboost-lightgbm-and-catboost-using-hyperopt-12bc41a271e?source=collection_home---4------1-----------------------

🔗 An Example of Hyperparameter Optimization on XGBoost, LightGBM and CatBoost using Hyperopt
Bonus: Hyperopt-Sklearn

​An Introduction to the Naive-Bayes Algorithm
How the Algorithm Behind Most Spam Filters Works\
https://towardsdatascience.com/an-introduction-to-the-naive-bayes-algorithm-be3bd692273e?source=collection_home---4------3-----------------------

🔗 An Introduction to the Naive-Bayes Algorithm
How the Algorithm Behind Most Spam Filters Works

​Neural Network
A simpler intuitive explanation.
https://towardsdatascience.com/neural-network-74f53424ba82?source=collection_home---4------4-----------------------

🔗 Neural Network
A simpler intuitive explanation.

​3 lessons I learned as a first year Data Science grad student with no experience.
https://towardsdatascience.com/3-lessons-i-learned-as-a-first-year-data-science-grad-student-with-no-experience-86449c90a5ff?source=collection_home---4------1-----------------------

🔗 3 lessons I learned as a first year Data Science grad student with no experience.
Even with college under my belt, Grad School has it’s own set of challenges.

Introduction to Machine Learning Guide. #python #AI Neural Network from Scratch in Python Microsoft
https://www.youtube.com/watch?v=UQlzgna62u4

🎥 Introduction to Machine Learning Guide. #python #AI Neural Network from Scratch in Python Microsoft
👁 1 раз ⏳ 3091 сек.
https://www.AiUpNow.com
Feel Free to Visit us & Don't Forget to Subscribe!
www.BruceDayne.com

Machine Learning, a prominent topic in Artificial Intelligence domain, has been in the spotlight for quite some time now. This area may offer an attractive opportunity, and starting a career in it is not as difficult as it may seem at first glance. Even if you have zero-experience in math or programming, it is not a problem. The most important element of your success is purely your own interest and motivation to

Artificial Intelligence and Machine Learning in Pediatric Biomedical Research

🎥 Artificial Intelligence and Machine Learning in Pediatric Biomedical Research
👁 1 раз ⏳ 3400 сек.
Prof. Judith Dexheimer, Associate Professor at Cincinnati Children's Hospital Medical Center

Dr. Dexheimer is an Associate Professor of Pediatrics at Cincinnati Children’s Hospital Medical Center and the University of Cincinnati. She is a clinical informaticist working on the development and implementation of machine learning applications into clinical care. Her research focus areas include machine learning techniques, real-time patient identification system, disparate data merging, and applications of cli

Tensorflow 2.0 Keras - python - Mastery Series

🎥 Tensorflow 2.0 Keras - python - Mastery Series
👁 1 раз ⏳ 464 сек.
This is the first video on the Tensorflow 2.0 Series
Getting started with first program

​Тренировка по машинному обучению 3 августа 2019

🔗 Тренировка по машинному обучению 3 августа 2019
Тренировки по машинному обучению — это открытый митап, на который мы приглашаем участников разных соревнований в сфере анализа данных чтобы познакомиться, рассказать про задачи и опыт участия в конкурсах, пообщаться и обменяться опытом. С докладами выступают успешные участники последних соревнований на Kaggle и других платформах. Они расскажут, какие техники и методы использовали в решениях они сами, а какие помогли их конкурентам. Программа 12.00 — 12.30 | Илья Ларченко — Kaggle Freesound Audio Tagging 2

​Ограничения машинного обучения

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
Большинство людей, читающих эту статью, вероятно, знакомы с машинным обучением и соответствующими алгоритмами, используемыми для классификации или прогнозирования результатов на основе данных. Тем не менее, важно понимать, что машинное обучение не является решением всех проблем. Учитывая полезность машинного обучения, может быть трудно согласиться с тем, что иногда это не лучшее решение проблемы.
#BigData
#Машинноеобучениe
#Искусственныйинтеллект
https://habr.com/ru/post/462365/

🔗 Ограничения машинного обучения
Привет, Хабр! Представляю вашему вниманию перевод статьи “The Limitations of Machine Learning“ автора Matthew Stewart. Большинство людей, читающих эту статью, в...

​Tighten the Towel! Simulating Liquid-Fabric Interactions

🔗 Tighten the Towel! Simulating Liquid-Fabric Interactions
📝 The paper "A Multi-Scale Model for Simulating Liquid-Fabric Interactions" is available here: http://www.cs.columbia.edu/cg/wetcloth/ ❤️ 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

​How to Develop a Pix2Pix GAN for Image-to-Image Translation
https://machinelearningmastery.com/how-to-develop-a-pix2pix-gan-for-image-to-image-translation/

🔗 How to Develop a Pix2Pix GAN for Image-to-Image Translation
The Pix2Pix Generative Adversarial Network, or GAN, is an approach to training a deep convolutional neural network for image-to-image translation tasks. The careful configuration of architecture as a type of image-conditional GAN allows for both the generation of large images compared to prior GAN models (e.g. such as 256×256 pixels) and the capability of performing …