Finally taking the first step into personal branding with my new blog! Sharing my journey of figuring things out, one post at a time. Check out why I’m starting to blog & where I hope it leads. #PersonalBranding#Blogging#CareerGrowth https://t.co/gIP2GR20lk
🔥 Introducing... the ML Reproducibility Challenge 2020! The 4th annual edition now expands to cover papers from 7 major ML conferences: NeurIPS, EMNLP, ACL, ICML, ICLR, CVPR and ECCV. Find more here at Papers With Code: https://t.co/URtsRPgw24
It’s official: CYBATHLON 2020 will take place on 13 – 14 November 2020 – globally and in a new format. Watch the brand new trailer now! https://t.co/TJZuo87sm1 #cybathlon2020globaledition#getreadyforcybathlon
CYBATHLON 2020 postponed due to Coronavirus!
Due to the current developments around the coronavirus, we are forced to postpone the #CYBATHLON2020 until 19-20 September 2020.
@tkasasagi Data Structures by Seymour Lipschutz, and Introduction to Algorithms by Thomas H Cormen, Charles Leiserson, Ronald L Rivest and Clifford Stein. The best in my opinion 😬😬
I spent half a year digging into @OpenAI, the SF-based AI research lab, originally founded by @elonmusk. I started with a few simple questions: Who are they? What are their goals? How do they work? After nearly three dozen interviews, I found so much more. https://t.co/wheK6r3r8j
With 4.5B parallel sentences in 576 language pairs, CCMatrix is the largest data set of high-quality, web-based bitexts for training translation models. Now Facebook AI is sharing tools for other researchers to use this corpus for their work. https://t.co/uvBbfjPTk5
We often hear that AI systems must provide explanations and establish causal relationships, particularly for life-critical applications.
Yes, that can be useful. Or at least reassuring....
1/n
Help revolutionize the world with full self-driving by joining us at Tesla Autopilot: https://t.co/ekekjKDOZF It is very hard to find other places where AI expertise makes as much of a difference on as big of a problem.
Added ImageNet validation results for 164 pretrained #PyTorch models on several datasets, incl ImageNet-A, ImageNetV2, and Imagenet-Sketch. No surprise, models with exposure to more data do quite well. Without extra, EfficientNets are holding their own. https://t.co/RopgL6OdNG