​This Will Change the Way You Look at GANs

🔗 This Will Change the Way You Look at GANs
Real-time visualizations of GAN learning and mode collapse

​A simulation framework to analyze airplane boarding methods

🔗 A simulation framework to analyze airplane boarding methods
Developing a Python program to calculate boarding times for various configurations and to visualize the boarding procedure

🎥 Applied Machine Learning - Peter Heiberg
👁 1 раз ⏳ 1838 сек.
In this talk Peter will tell the story about how he applied machine learning to enhance the user experience of data entry and search using natural language processing and face recognition in one of the spare time projects, a large crowd sourced wiki. The results of those enhancements exceeded his wildest expectations.

Speaker Peter Heiberg
A seasoned software developer with a passion for sharing knowledge. He has been working as a consultant the last 9 years. Peter has spent the last 20 years developing li

🎥 Top 10 Artificial Intelligence Technologies in 2020 | Artificial Intelligence Trends | Edureka
👁 1 раз ⏳ 622 сек.
🔥 Machine Learning Engineer Masters Program: https://www.edureka.co/masters-program/machine-learning-engineer-training
This Edureka video on "Top 10 Technologies in AI" will list out the top trending technologies that are going to take over the IT industries with the help of Artificial Intelligence. These technologies are most likely to start showing their dominance in the market from 2020 itself.

-----------------------------------------------------------

🔵 Post Graduate Program in AI and Machine Learni

​Anatomy of an AI System

🔗 Anatomy of an AI System
Anatomy of an AI System - The Amazon Echo as an anatomical map of human labor, data and planetary resources. By Kate Crawford and Vladan Joler (2018)

​Introduction to Deep Learning

📝 Skansi_S_-_Introduction_to_Deep_Learning_-_2018.pdf - 💾3 893 279

​Good Feature Matching: Towards Accurate, Robust VO/VSLAM with Low Latency

https://github.com/ivalab/gf_orb_slam2

https://arxiv.org/abs/2001.00714v1

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 ivalab/gf_orb_slam2
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities - ivalab/gf_orb_slam2

​Камера с функцией слежения за объектом
Хочу сделать автономного дрона, который бы сам мог найти дорогу к цели и обратно, при этом обойти все препятствия ни кого не задев. Решил начать с нейросети и вебки. Так и получился этот проект

🔗 Камера с функцией слежения за объектом
Хочу сделать автономного дрона, который бы сам мог найти дорогу к цели и обратно, при этом обойти все препятствия ни кого не задев. Решил начать с нейросети и ве...

​Imagining a world without Transformers — Single Headed Attention RNN

🔗 Imagining a world without Transformers — Single Headed Attention RNN
Distilling key ideas from one of the most entertaining NLP papers picturing a world without the BERT family of models

​Donald Knuth: Algorithms, Complexity, Life, and The Art of Computer Programming | AI Podcast

🔗 Donald Knuth: Algorithms, Complexity, Life, and The Art of Computer Programming | AI Podcast
Donald Knuth is one of the greatest and most impactful computer scientists and mathematicians ever. He is the recipient in 1974 of the Turing Award, considered the Nobel Prize of computing. He is the author of the multi-volume work, the magnum opus, The Art of Computer Programming. He made several key contributions to the rigorous analysis of the computational complexity of algorithms. He popularized asymptotic notation, that we all affectionately know as the big-O notation. He also created the TeX typesett

​Unbalanced data loading for multi-task learning in PyTorch

🔗 Unbalanced data loading for multi-task learning in PyTorch
Working on multi-task learning (MTL) problems require unique training setup, mainly in terms of data handling, model architecture, and…

​Calculating Catchment with Human Mobility Data

🔗 Calculating Catchment with Human Mobility Data
Leveraging Human Mobility Data to identify potential customers

​A Very Unlikely Chess Game

🔗 A Very Unlikely Chess Game
Almost 25 years after Kasparov vs. Deep Blue, another seminal man vs. machine matchup: Neither competitor has much to be proud of here. White has a poor opening. Black screws up and loses his queen…

🎥 Deep Learning for Higgs and New Physics Searches at the LHC
👁 1 раз ⏳ 3224 сек.
Professor Javier Duarte
2019 11 11
University of California, San Diego

Since the discovery of the Higgs boson at the Large Hadron Collider in 2012, developments in deep learning have expanded our ability to study the production of Higgs bosons and other particles with very large momenta. By studying these particles, we may be able to discover new physics at very high energy scales inaccessible directly at the LHC. I will explain these searches and talk about the direction that deep learning is taking in p

🎥 Deep Learning Formulas for NLP Applications | Chenglong Chen | Kaggle
👁 1 раз ⏳ 1633 сек.
Content note: Speaker is presenting in Mandarin but presentation and subtitles are in English.

Kaggle Days China edition was held on October 19-20 at Damei Center, Beijing.

More than 400 data scientists and enthusiasts gathered to learn, make friends, and compete in a full-day offline competition.

Kaggle Days is produced by LogicAI and Kaggle.

About LogicAI:
LogicAI is a boutique Data Science consultancy company owned by Kaggle fans and Grandmasters. As a global company, they do custom end-to-end AI and

​Использование Clickhouse в качестве замены ELK, Big Query и TimescaleDB
Clickhouse — это столбцовая система управления базами данных для онлайн обработки аналитических запросов (OLAP) с открытым исходным кодом, созданная Яндексом. Ее используют Яндекс, CloudFlare, VK.com, Badoo и другие сервисы по всему миру для хранения действительно больших объемов данных (вставка тысяч строк в секунду или петабайты данных, хранящихся на диске).

В обычной, «строковой» СУБД, примерами которых служат MySQL, Postgres, MS SQL Server, данные хранятся в таком порядке:

При этом значения, относящиеся к одной строке, физически хранятся рядом. В столбцовых СУБД значения из разных столбцов хранятся отдельно, а данные одного столбца – вместе:

🔗 Использование Clickhouse в качестве замены ELK, Big Query и TimescaleDB
Clickhouse — это столбцовая система управления базами данных для онлайн обработки аналитических запросов (OLAP) с открытым исходным кодом, созданная Яндексом. Ее...

​MuZero: DeepMind’s New AI Mastered More Than 50 Games

🔗 MuZero: DeepMind’s New AI Mastered More Than 50 Games
❤️ Check out Linode here and get $20 free credit on your account: https://www.linode.com/papers 📝 The paper "Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model" is available here: https://arxiv.org/abs/1911.08265 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Christian Ahlin, Claudio Fernandes, Daniel Hasegan, Dan Kennedy, Dennis

​Data project checklist

https://www.fast.ai//2020/01/07/data-questionnaire/

Designing great data products
The Drivetrain Approach: A four-step process for building data products.

https://www.oreilly.com/radar/drivetrain-approach-data-products/

🔗 Data project checklist
There's a lot more to creating useful data projects than just training an accurate model

​Как сделать бота, который превращает фото в комикс. Часть вторая. Обучение модели
⇨ Первая часть

И снова здравствуйте!

Как вы могли заметить, праздники несколько подкосили график выхода статей.
Думаю, многие за это время успели если не полностью обучить свою модель, то хотя бы поэкспериментировать с различными наборами данных.

1. Ставим дистрибутив
2. Качаем фотки
3. ???
4. Profit!

Если же вам было не до этих наших нейросетей, или вы начинаете чтение с этой статьи, то, как говорится, нет времени объяснять, берем дистрибутив, качаем нужные фотки, и поехали!

🔗 Как сделать бота, который превращает фото в комикс. Часть вторая. Обучение модели
⇨ Первая часть И снова здравствуйте! Как вы могли заметить, праздники несколько подкосили график выхода статей. Думаю, многие за это время успели если не полн...

🎥 Vahid Moosavi - 'Machine learning literacy for designers & engineers'
👁 1 раз ⏳ 3761 сек.
Dr Vahid Moosavi (Senior Researcher, CAAD, ETH)

Machine learning literacy for designers and engineers

Machine learning and data together offer a universal way of looking at the world phenomena, which is radically different than the classical expert-based disciplinary research. This new approach of computational modeling has inverted the classical notion of expertise from “having the answers to the known questions” to “learning to ask good questions”. This will have important consequences on the ways we th