Twitter | Pretraživanje | |
Rheza Harliman
Books, Tech, Android Dev, Machine Learning (image) | Engineer on weekdays ↔️ Goalkeeper on weekends | Introvert | -Balancing the Imbalanced- 🇮🇩🇯🇵
12.572
Tweetovi
1.022
Pratim
701
Osobe koje vas prate
Tweetovi
Rheza Harliman proslijedio/la je tweet
Machine Learning Tokyo 31. sij
Check out our Machine Learning and Deep Learning EN-JP dictionary. Feel free to send a PR or raise an issue to help make this repo more useful for English-Japanese speakers!  
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Richard Feynman 30. sij
Feynman Lessons for Learning: 🧠 1) Understanding is more important than memorization! 2) Learn principles, not formulas. 3) Ask questions! 4) Read Books every day. 5) Teaching is a powerful tool to learning.
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
OpenAI 30. sij
We're standardizing OpenAI's deep learning framework on PyTorch to increase our research productivity at scale on GPUs (and have just released a PyTorch version of Spinning Up in Deep RL):
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Machine Learning Tokyo 31. sij
Passionate about AI and community building? 🤖 We are looking for an Event-/Community Manager to join the team! 🙌 Starting with 10h/week. Students based in Tokyo are welcome to apply!
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Kasia_Kulma 29. sij
data people! I've created a curated list of open data/API/ML projects relating to . Make a pull request or raise an issue if you'd like to contribute. And of course, use it and explore it to your heart content!
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Machine Learning Tokyo 28. sij
We held a fantastic meetup on "Recommendation Systems in Production" with Senior Engineer (Data Science) . His slides are available now!
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Grace Lindsay 22. sij
My blogpost on how & why we use convolutional neural networks as a model of the visual system is probably the most read thing I've ever written and it's now been expanded & updated into a proper review article, complete with 136 references & 5 new figures!
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Facebook AI 24. sij
We're releasing mBART, a new seq2seq multilingual pretraining system for machine translation across 25 languages. It gives significant improvements for document-level translation and low-resource languages. Read our paper to learn more:
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
David Berthelot 22. sij
FixMatch: focusing on simplicity for semi-supervised learning and improving state of the art (CIFAR 94.9% with 250 labels, 88.6% with 40). Collaboration with Kihyuk Sohn, Nicholas Carlini
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Ming Cheuk 21. sij
I wrote a blog post about the machine reading comprehension demo I recently shared. Tutorial notebook at the end if you want to train your own!
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
hardmaru 22. sij
BayesNet: A library for drawing Bayesian networks, graphical models and directed factor graphs in LaTeX.
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman 22. sij
Odgovor korisniku/ci @heiga_zen
アンドロイド発見!🤩
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Machine Learning Tokyo 22. sij
More ML. More projects. More remote opportunities. Join the community.
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Emil Wallner 20. sij
How to get into machine learning without a degree, alternatives to traditional education, building a portfolio, applying for ML jobs, interviews, getting into research, and indie research ideas. I had an ace chat with at . Enjoy!
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Lex Fridman 19. sij
Here's a lecture by Andrew Trask () on privacy-preserving AI as part of the MIT Deep Learning lecture series. Preserving privacy boosts our ability to do science at a large-scale and to engineer intelligent systems that learn from data:
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Google Devs Japan 20. sij
TensorFlow Lite を使って、iOS 端末で人の動きをトラックしましょう!💃 📹 さんが開発したアプリは TensorFlow Lite がリアルタイムでカメラの入力を受け取り、身体の主要部位にオーバーレイをします。 こちらでお試しください→
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Lex Fridman 14. sij
Here's my conversation with Daniel Kahneman, Nobel Prize winning economist and psychologist, author of Thinking Fast and Slow. We talk about two systems of thought in the human mind and their connection to deep learning, AI, and autonomous vehicles.
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
Brenden Lake 14. sij
The source code for meta seq2seq learning is now available through . You can reproduce the experiments from my paper, or run memory-based meta learning on other seq2seq problems.
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman 14. sij
Odgovor korisniku/ci @reiinakano
Congrats Rei! 👏
Reply Retweet Označi sa "sviđa mi se"
Rheza Harliman proslijedio/la je tweet
hardmaru 12. sij
The Case for Bayesian Deep Learning ”Bayesian or not, the prior will certainly be imperfect. Avoiding an important part of the modelling process because one has to make assumptions, however, will often be a worse alternative than an imperfect assumption.”
Reply Retweet Označi sa "sviđa mi se"