admin, Author at Bag of Tricks in Machine Learning - Page 2 of 8

ACL 2019 best papers

August 4, 2019August 4, 2019 by admin

http://www.acl2019.org/EN/winners-of-acl-2019-best-paper-awards.xhtml

spaCy transformer

August 4, 2019August 4, 2019 by admin

Say hello to spacy-pytorch-transformers!

🛸 BERT, XLNet & GPT-2 in your spaCy pipeline
🤗 Based on @HuggingFace's pytorch-transformers
🎚️ Fine-tune pretrained models on your task
📦 Model packages for English & German
🚀 Token alignment, similarity & morehttps://t.co/3ftjt6pXwi
— spaCy (@spacy_io) August 2, 2019

Advances in Conversational AI by FAIR

August 4, 2019August 4, 2019 by admin

https://ai.facebook.com/blog/advances-in-conversational-ai

Affordable AI

July 25, 2019July 22, 2019 by admin

Concern: https://arxiv.org/abs/1906.02243

Good examples:

$40 to train imagenet: https://www.fast.ai/2018/08/10/fastai-diu-imagenet
Fastest end2end ASR: https://github.com/facebookresearch/wav2letter
Neural architecture search in 1.5 days on a single GPU: https://arxiv.org/abs/1806.09055

[fun] The hidden secret of ML

July 20, 2019July 20, 2019 by admin

The hidden secret of ML from datascience

[Fun] training for model

July 20, 2019July 20, 2019 by admin

Still waiting… from ProgrammerHumor

Graph net collection

July 18, 2019July 18, 2019 by admin

"Awesome Graph Classification" — A collection of graph classification methods, covering embedding, deep learning, graph kernel, and factorization papers with reference implementations https://t.co/ugpL3xSvf1
— Sebastian Raschka (@rasbt) July 16, 2019

Yoav Goldberg: The missing elements in NLP (spaCy IRL 2019)

July 13, 2019July 13, 2019 by admin

Attention mechanism

July 6, 2019July 6, 2019 by admin

Attention for interpretability:

Learning to Explain: https://arxiv.org/abs/1802.07814
Attention is not Explanation: https://arxiv.org/abs/1902.10186
Is Attention Interpretable?: https://arxiv.org/abs/1906.03731

Reviews:

NLP today

July 6, 2019July 6, 2019 by admin

NLP Today 😄 @yoavgo @spacy_io #spaCyIRL pic.twitter.com/ZXm4QeAIhF
— Christian Rehm (@Wadenschwinger) July 6, 2019

ShujianFollow

Retweet on Twitter Shujian Retweeted

Julien Plu @julienplu·

Ever wanted to deploy the fast @TensorFlow models from @huggingface Transformers in TensorFlow Serving? Check out the following:
Tutorial: https://huggingface.co/blog/tf-serving
Notebook: https://tinyurl.com/y6r5ch2v

Reply on Twitter 1354099325996048385 Retweet on Twitter 135409932599604838547 Like on Twitter 1354099325996048385199 Twitter 1354099325996048385

Retweet on Twitter Shujian Retweeted

Graham Neubig @gneubig·

If you're looking for some nice videos on cutting-edge NLP research, check out the @LTIatCMU YouTube Channel with presentations by LTI members and guest speakers! https://www.youtube.com/c/LTIatCMU

我们的中国朋友也可以观看bilibili：https://space.bilibili.com/1377044784

Reply on Twitter 1351922935469060096 Retweet on Twitter 135192293546906009678 Like on Twitter 1351922935469060096369 Twitter 1351922935469060096

Retweet on Twitter Shujian Retweeted

Gregory Koberger @gkoberger·

Now this is patience....

Reply on Twitter 1351271003989544965 Retweet on Twitter 13512710039895449652204 Like on Twitter 135127100398954496516086 Twitter 1351271003989544965

Retweet on Twitter Shujian Retweeted

arXiv in review @arxiv_in_review·

#NeurIPS2020 Parameterized Explainer for Graph Neural Network. (arXiv:2011.04573v1 [cs\.LG] CROSS LISTED) http://arxiv.org/abs/2011.04573

Reply on Twitter 1346988622566850563 Retweet on Twitter 13469886225668505631 Like on Twitter 13469886225668505632 Twitter 1346988622566850563

Retweet on Twitter Shujian Retweeted

Facebook AI@facebookai·

We’re open-sourcing a new system to train computer vision models using Transformers. Data-efficient image Transformers (DeiT) is a high-performance image classification model requiring less data & computing resources to train than previous AI models. https://ai.facebook.com/blog/data-efficient-image-transformers-a-promising-new-technique-for-image-classification/

Reply on Twitter 1341957881059373056 Retweet on Twitter 1341957881059373056547 Like on Twitter 13419578810593730562050 Twitter 1341957881059373056