​Building brain-inspired computing

🔗 Building brain-inspired computing
Dmitri Strukov (an electrical engineer, University of California at Santa Barbara), Giacomo Indiveri (an electrical engineer, University of Zurich), Julie Grollier (a material physicist, Unite Mixte de Physique CNRS) and Stefano Fusi (a neuroscientist, Columbia University) talked to Nature Communications about the opportunities and challenges in developing brain-inspired computing technologies, namely neuromorphic computing, and advocated effective collaborations crossing multidisciplinary research areas to support this emerging community.

​Google’s BERT changing the NLP Landscape

🔗 Google’s BERT changing the NLP Landscape
We write a lot about open problems in Natural Language Processing. We complain a lot when working on NLP projects. We pick on inaccuracies…

​Reinforcement Learning for Mobile Games

🔗 Reinforcement Learning for Mobile Games
Learning to play Android games at scale using state-of-the-art Reinforcement Learning

​Solving NLP Problems with BERT | Yuanhao Wu | Kaggle

🔗 Solving NLP Problems with BERT | Yuanhao Wu | Kaggle
Content note: Presenter speaks Mandarin but slide and subtitles are in English language. 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 Data S

​Т — значит творчество
Пока весь мир, вместо того, чтобы нарезать салаты готовиться к встрече Нового года, следит за развитием ситуации с nginx, мы решили не усугублять и не готовить серьезную научную статью, не шокировать технологиями наступившего будущего и не грузить очень хитрым алгоритмом. Мы тоже пользуемся nginx и надеемся, что и с его создателями и с ним все будет хорошо. И нам (да и не только нам) важно, чтобы ситуация разрешилась не как подарок Деда Мороза, а как естественный ход событий.

🔗 Т — значит творчество
Пока весь мир, вместо того, чтобы нарезать салаты готовиться к встрече Нового года, следит за развитием ситуации с nginx, мы решили не усугублять и не готовить с...

​Книга Data Science Essentials in Python

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

📝 1zinoviev_d_data_science_essentials_in_python_collect_organiz.pdf - 💾10 881 637

​Why Going from Implementing Q-learning to Deep Q-learning Can Be Difficult

🔗 Why Going from Implementing Q-learning to Deep Q-learning Can Be Difficult
3 Questions I was Afraid to Ask (and my Tensorflow 2.0 Template)

Learning by Cheating

https://www.youtube.com/watch?v=u9ZCxxD-UUw&feature=youtu.be

https://arxiv.org/abs/1912.12294

🎥 Learning by Cheating
👁 2 раз ⏳ 259 сек.
Learning by Cheating
Dian Chen, Brady Zhou, Vladlen Koltun, Philipp Krähenbühl
Conference on Robot Learning (CoRL 2019)


Code: https://github.com/dianchen96/LearningByCheating

​These Natural Images Fool Neural Networks

🔗 These Natural Images Fool Neural Networks
❤️ Check out Weights & Biases here and sign up for a free demo: https://www.wandb.com/papers Their blog post on training a neural network is available here: https://www.wandb.com/articles/mnist 📝 The paper "Natural Adversarial Examples" and its dataset are available here: https://arxiv.org/abs/1907.07174 https://github.com/hendrycks/natural-adv-examples Andrej Karpathy's image classifier: https://cs.stanford.edu/people/karpathy/convnetjs/demo/cifar10.html 🙏 We would like to thank our generous Patreon

​2019 Artificial Intelligence Breakthrough
https://www.google.com/amp/s/www.forbes.com/sites/tomtaulli/2019/12/07/this-years-ai-artificial-intelligence-breakthroughs/amp/

🔗 This Year’s AI (Artificial Intelligence) Breakthroughs
Yes, the innovation is continuing at a furious pace.

​This Insect Has The Only Mechanical Gears Ever Found in Nature

🔗 This Insect Has The Only Mechanical Gears Ever Found in Nature
The small hopping insect Issus coleoptratus uses toothed gears on its joints to precisely synchronize the kicks of its hind legs as it jumps forward

​Using Meta-Learning to Train Agents to Learn Generic Concepts

🔗 Using Meta-Learning to Train Agents to Learn Generic Concepts
During this holiday season, I am revisiting some of the most important AI papers of the last few months.

​Closet Data Scientists — Who Are They?

🔗 Closet Data Scientists — Who Are They?
The unassuming next generation of Data Scientists

​Is Deep Learning the Future of Medical Decision Making?

https://thegradient.pub/is-deep-learning-the-future-of-medical-decision-making/

🔗 Is Deep Learning the Future of Medical Decision Making?
Healthcare is often spoken of as a field that is on the verge of an AI revolution. Big names in AI such as Google DeepMind, publicise their efforts in healthcare, claiming that “AI is poised to transform medicine.” But how impactful has AI been so far? Have we really identified

​Why UMAP is Superior over tSNE

🔗 Why UMAP is Superior over tSNE
Does initialization really matter?

​ML for Optimization Problems | Qingchen Wang | Kaggle Days

🔗 ML for Optimization Problems | Qingchen Wang | Kaggle Days
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 Data Science development projects as well as trainings for C-level management and tech teams.

​"Extreme Relative Pose Network under Hybrid Representations"

https://github.com/SimingYan/Hybrid_Relative_Pose

Article: https://arxiv.org/abs/1912.11695

🔗 SimingYan/Hybrid_Relative_Pose
Implementation of Paper "Extreme Relative Pose Network under Hybrid Representations" - SimingYan/Hybrid_Relative_Pose

​Machine Learning with Spark

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

📝 Pentreath - Machine Learning with Spark.pdf - 💾4 909 606