Data Science by ODS.ai 🦜

Logo of telegram channel opendatascience — Data Science by ODS.ai 🦜
Topics from channel:
Book
جان
Comix
Dl
جان
Openai
Gpt
Dalle
Python
Opensource
All tags
Logo of telegram channel opendatascience — Data Science by ODS.ai 🦜
Topics from channel:
Book
جان
Comix
Dl
جان
Openai
Gpt
Dalle
Python
Opensource
All tags
Channel address: @opendatascience
Categories: Technologies
Language: English
Subscribers: 48.41K
Description from channel

First Telegram Data Science channel. Covering all technical and popular staff about anything related to Data Science: AI, Big Data, Machine Learning, Statistics, general Math and the applications of former. To reach editors contact: @opendatasciencebot

Ratings & Reviews

2.67

3 reviews

Reviews can be left only by registered users. All reviews are moderated by admins.

5 stars

1

4 stars

0

3 stars

0

2 stars

1

1 stars

1


The latest Messages 23

2021-01-21 14:55:13 S+SSPR Workshop: An online workshop on Statistical techniques in Pattern Recognition and Structural and Syntactic Pattern Recognition.

The event is free to attend, it is happening today and tomorrow (online) with a fantastic list of keynotes: Nicholas Carlini, Michael Bronstein, Max Welling, Fabio Roli — professors and researcher in the field of geometric deep learning, pattern recognition and adversarial learning.

Live YouTube Streaming: https://www.youtube.com/channel/UCjA0Mhynad2FDlNaxzqGLhQ

Official Program here: https://www.dais.unive.it/sspr2020/program/

Don't miss it!
16.4K views11:55
Open / Comment
2021-01-19 15:06:50 NLP Highlights of 2020

by Sebastian Ruder:

1. Scaling up—and down
2. Retrieval augmentation
3. Few-shot learning
4. Contrastive learning
5. Evaluation beyond accuracy
6. Practical concerns of large
7. LMs
8. Multilinguality
9. Image Transformers
10. ML for science
11. Reinforcement learning

https://ruder.io/research-highlights-2020/
15.6K views12:06
Open / Comment
2021-01-18 12:42:16
oops :kekeke:


paper: https://arxiv.org/abs/2012.15332
14.8K viewsedited  09:42
Open / Comment
2021-01-14 20:47:46 Choosing Transfer Languages for Cross-Lingual Learning

Given a particular task low-resource language and NLP task, how can we determine which languages we should be performing transfer from?
If we train models on the top K transfer languages suggested by the ranking model and pick the best one, how good is the best model expected to be?

In the era of transfer learning now we have a possibility not to collect the massive data for each language, but using already pretrained model achieve good scores training on smaller data. But how should we choose the language from which we can transfer knowledge? Will it be okay to transfer from English to Chinese or from Russian to Turkish?

The paper investigate on this question. The features the authors created to detect the best transfer language are the follows:

* Dataset Size: as simple as it is — do we have enough data in transfer language with respect to ratio to train language?
* Type-Token Ratio: diversity of both languages;
* Word Overlap and Subword Overlap: kind of similarity of languages; it is very good if both languages have as much the same words as possible;
* Geographic distance: are the languages from the territories that are close on the Earth surface?
* Genetic distance: are they close to each other in terms of language genealogical tree?
* Inventory distance: are they sound familiar?

The idea is pretty simple and clear but very important for studies of multilingual models.

The post is based on reading task from Multilingual NLP course by CMU (from the post).
16.6K views17:47
Open / Comment
2021-01-12 13:06:52 ​​Interactive and explorable explanations

Collection of links to different explanations of how things work.

Link: https://explorabl.es
How network effect (ideas, diseases) works: https://meltingasphalt.com/interactive/going-critical/
How trust works: https://ncase.me/trust/

#howstuffworks #explanations
15.4K views10:06
Open / Comment
2021-01-11 11:28:44 ​​Characterising Bias in Compressed Models

Popular compression techniques turned out to amplify bias in deep neural networks.

ArXiV: https://arxiv.org/abs/2010.03058

#NN #DL #bias
14.5K views08:28
Open / Comment
2021-01-09 15:21:55 Open Software Packaging for Science

#opensource alternative to #conda.

Mamba (drop-in replacement) direct link: https://github.com/TheSnakePit/mamba
Link: https://medium.com/@QuantStack/open-software-packaging-for-science-61cecee7fc23

#python #packagemanagement
15.0K views12:21
Open / Comment
2021-01-06 12:55:05 multilingual datasets

- 611 datasets you can download in one line of python;
- 467 languages covered, 99 with at least 10 datasets;
- efficient pre-processing to free you from memory constraints;

https://github.com/huggingface/datasets
16.5K views09:55
Open / Comment
2021-01-06 03:03:17 ​​ New breakthrough on text2image generation by #OpenAI

DALL·E: Creating Images from Text

This architecture is capable of understanding style descriptions as well as complex relationship between objects in context.

That opens whole new perspective for digital agencies, potentially threatening stock photo sites and new opportunies for regulations and lawers to work on.

Interesting times!

Website: https://openai.com/blog/dall-e/

#GAN #GPT3 #openai #dalle #DL
14.6K views00:03
Open / Comment
2020-12-31 14:31:12
2020: A Year Full of Amazing AI Papers — A Review

https://www.kdnuggets.com/2020/12/2020-amazing-ai-papers.html

@ai_machinelearning_big_data
15.4K views11:31
Open / Comment