Skip to content

Bag of Tricks in Machine Learning

Public Personal Notebook

  • Home
  • random
  • paper
  • list
  • nlp
  • reinforcementlearning
  • gan
  • cv

Real-Time NLU with BERT Using TensorRT

August 16, 2019 by admin

https://devblogs.nvidia.com/nlu-with-tensorrt-bert/

Categories Uncategorized Leave a comment

Megatron-LM by Nvidia

August 16, 2019 by admin

Research on training transformer language models at scale, including BERT:

https://github.com/NVIDIA/Megatron-LM

Categories Uncategorized Leave a comment

Personal VAD by Google

August 16, 2019 by admin

https://arxiv.org/abs/1908.04284

Personal VAD: Speaker-Conditioned Voice Activity Detection

Shaojin Ding, Quan Wang, Shuo-yiin Chang, Li Wan, Ignacio Lopez Moreno

Comments: To be submitted to ICASSP 2020Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Machine Learning (stat.ML)

Categories Uncategorized Leave a comment

ACL 2019 best papers

August 4, 2019 by admin

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

Categories Uncategorized Leave a comment

spaCy transformer

August 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
Categories Uncategorized Leave a comment

Advances in Conversational AI by FAIR

August 4, 2019 by admin
https://ai.facebook.com/blog/advances-in-conversational-ai
Categories Uncategorized Leave a comment

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

Categories Uncategorized Leave a comment

[fun] The hidden secret of ML

July 20, 2019 by admin
The hidden secret of ML from datascience
Categories Uncategorized Leave a comment

[Fun] training for model

July 20, 2019 by admin
Still waiting… from ProgrammerHumor
Categories Uncategorized Leave a comment

Graph net collection

July 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
Categories Uncategorized Leave a comment
Post navigation
Older posts
Newer posts
← Previous Page1 Page2 Page3 … Page8 Next →

Best practice to follow this website

  1. In Feedly, click “add content”
  2. Input the url “bagoftricks.ml” and follow

ShujianFollow

Shujian
Retweet on TwitterShujian Retweeted
achowdheryAakanksha Chowdhery@achowdhery·
11 May

#GoogleIO2022 showcases reasoning and multilingual capabilities of PaLM model.
https://youtu.be/nP-nMZpLM1A?t=7240
Blog: https://ai.googleblog.com/2022/04/pathways-language-model-palm-scaling-to.html
arXiv: https://arxiv.org/abs/2204.02311

2
Reply on Twitter 1524473852704681984Retweet on Twitter 1524473852704681984131Like on Twitter 1524473852704681984726Twitter 1524473852704681984
Retweet on TwitterShujian Retweeted
christopherChristopher Akiki@christopher·
5 May

A rather hidden @huggingface tokenizers feature: the Visualizer.

Reply on Twitter 1522226910171914241Retweet on Twitter 152222691017191424115Like on Twitter 1522226910171914241104Twitter 1522226910171914241
Retweet on TwitterShujian Retweeted
MetaAIMeta AI@MetaAI·
3 May

Today Meta AI is sharing OPT-175B, the first 175-billion-parameter language model to be made available to the broader AI research community. OPT-175B can generate creative text on a vast range of topics. Learn more & request access: https://ai.facebook.com/blog/democratizing-access-to-large-scale-language-models-with-opt-175b

Reply on Twitter 1521489996145958914Retweet on Twitter 1521489996145958914659Like on Twitter 15214899961459589142339Twitter 1521489996145958914
Retweet on TwitterShujian Retweeted
StackOverflowStack Overflow@StackOverflow·
2 May

I think I can, I think I can, I think I can. #stackoverflowmemes #mememay

Reply on Twitter 1521236849003540483Retweet on Twitter 15212368490035404833123Like on Twitter 152123684900354048323115Twitter 1521236849003540483
Retweet on TwitterShujian Retweeted
jobergumJo Kristian Bergum@jobergum·
21 Apr

Super excited about these new features we are adding to Vespa, the leading vector database:

- Chose between post filtering or pre filtering at query time when combining vector search with filters
- Up to 2x speed up of hybrid retrieval combining sparse WAND and vector search

Reply on Twitter 1517210650388402178Retweet on Twitter 15172106503884021783Like on Twitter 151721065038840217837Twitter 1517210650388402178
Load More...

Categories

  • ml (2)
  • nlp (12)
  • papers (1)
  • random (8)
  • reinforcementlearning (1)
  • Uncategorized (57)

Tags

anomaly (1) automl (1) ctr (1) cv (2) data (1) distributedtraining (1) gan (1) kaggle (1) list (2) ml (2) NER (1) nlp (10) nn (1) paper (1) random (3) reinforcementlearning (1) sql (1)

Recent Posts

  • Version mismatch in embedding-based retrieval
  • NER with small strongly labeled and large weakly labeled data
  • A Survey of Data Augmentation Approaches for NLP
  • Data Augmentation in NLP
  • PyTorch nn.DistributedDataParallel

Archives

  • July 2021 (2)
  • June 2021 (1)
  • May 2020 (1)
  • October 2019 (1)
  • August 2019 (11)
  • July 2019 (8)
  • June 2019 (6)
  • May 2019 (1)
  • April 2019 (11)
  • March 2019 (4)
  • February 2019 (2)
  • January 2019 (32)

Recent Comments

    May 2022
    M T W T F S S
     1
    2345678
    9101112131415
    16171819202122
    23242526272829
    3031  
    « Jul    

    • 0
    • 3
    • 86,605
    • 42,922
    • 80
    • 0

    Recent Posts

    • Version mismatch in embedding-based retrieval
    • NER with small strongly labeled and large weakly labeled data
    • A Survey of Data Augmentation Approaches for NLP
    • Data Augmentation in NLP
    • PyTorch nn.DistributedDataParallel

    Categories

    • ml (2)
    • nlp (12)
    • papers (1)
    • random (8)
    • reinforcementlearning (1)
    • Uncategorized (57)

    Meta

    • Log in
    • Entries feed
    • Comments feed
    • WordPress.org
    © 2022 Bag of Tricks in Machine Learning • Built with GeneratePress