When ML models are deployed, data distributions evolving over time leads to a drop in performance. Our latest paper (theory and experiments) suggests we can use self-training on unlabeled data to maintain high performance
https://arxiv.org/pdf/2002.11361.pdf

❇️ @AI_Python_EN

You can use a method called one hot encoding.
https://hackernoon.com/what-is-one-hot-encoding-why-and-when-do-you-have-to-use-it-e3c6186d008f

Covid-19, your community, and you — a data science perspective

https://www.fast.ai/2020/03/09/coronavirus/

❇️ @AI_Python_EN

How neural structure learning can help avoid adversarial attack om models

https://medium.com/@omcar17/what-is-neural-structure-learning-4d4e43083df9

❇️ @AI_Python_EN

http://bit.ly/38PUGGO here's a list of most popular ML interview questions and answers.

Here's an update from Dan Jurafsky and the #acl2020nlp team re COVID19:

https://acl2020.org

#NLProc

Can a shiny app be a paper? Heck yeah!
Red question mark ornament
"Where to publish your Shiny App?"

https://buff.ly/3cOqSNU #rstats #rshiny

We have just released Multi-SimLex v1: a new multilingual #NLProc resource for semantic similarity. It covers 1,888 concept pairs across 12 typologically diverse langs, plus 66 xling data sets. .

https://multisimlex.com

Multi-SimLex provides a new, typologically diverse evaluation benchmark for representation learning models. See our paper for experiments and interesting analysis:

https://arxiv.org/pdf/2003.04866.pdf

But this is not all! We are also launching a collaborative initiative to extend Multi-SimLex to cover many more of the world’s languages! Please join us in this effort to create an extensive semantic similarity resource for the needs of contemporary multilingual #NLProc.We welcome your contributions for both small and major languages! Follow the guidelines at https://multisimlex.com to create and submit a Multi-Simlex -style dataset for your favourite language. All the
contributions will be shared with everyone via the Multi-SimLex site.

Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner.

abs: https://arxiv.org/abs/2002.05534v1

#rnn #machinelearning #ArtificialIntelligence #DeepLearning #

❇️ @AI_Python_EN

Introduction to Reinforcement Learning

By DeepMind : https://lnkd.in/dd2VNhH

#ArtificialIntelligence #DeepLearning #ReinforcementLearning

A PyTorch re-implementation of Generative Teaching Networks has been made available by GoodAIdev https://lnkd.in/giJBSw3 Nice to see! https://lnkd.in/gzGMJBn

Access 2 new free online courses
as of today on edXOnline
It's time to hone your #digitalintelligence knowledge and skills, even more if you're getting bored at home:
http://bit.ly/2WLF58R

#DeepLearning

❇️ @AI_Python_EN

Help us scale #COVID19 detection over the phone.

If you have a #COVID19 diagnosis or are healthy, consider recording a breathing sample anonymously at https://breatheforscience.com

We hope this data leads to techniques to help diagnosis of #COVID19 over the phone.

❇️ @AI_Python_EN

10 Useful ML Practices For Python Developers

Pratik Bhavsar:
https://medium.com/modern-nlp/10-great-ml-practices-for-python-developers-b089eefc18fc


#Python #MachineLearning #ArtificialIntelligence #DataScience #Programming

❇️ @AI_Python_EN

Contributor Derrick Mwiti with an overview of #TensorFlow MLIR—a mult-level intermediate representation designed to be a reusable and extensible compiler that works across the #DeepLearning landscape.
https://bit.ly/2Jt83T7

❇️ @AI_Python_EN

Excited to share that my first first-author paper - “Unsupervised Cross-lingual Representation Learning at Scale”

Link: https://arxiv.org/pdf/1911.02116.pdf

❇️ @AI_Python_EN

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

Input is images with known camera poses. Can't wait to disable all the sanity checks and see what this renders if I give it impossible geometry.

abs: https://arxiv.org/abs/2003.08934
site: http://matthewtancik.com/nerf

❇️ @AI_Python_EN

Breast cancer classification with Keras and Deep Learning

To analyze the cellular structures in the breast histology images we were instead leveraging basic computer vision and image processing algorithms, but combining them in a novel way.

Researcher: Adrian Rosebrock
Paper & codes : http://ow.ly/yngq30qjLye

#artificialintelligence #ai #machinelearning #deeplearning #bigdata #datascience

❇️ @AI_Python_EN

Very good news. Dataproc now lets you use NVIDIA GPUs to accelerate XGBoost in a Spark pipeline. This combination can speed up machine learning development and training up to 44x and reduce costs 14x when using XGBoost. With this kind of GPU acceleration for XGBoost, you can get better performance, speed, accuracy, and reduced TCO, plus an improved experience when deploying and training models. Spinning up elastic Spark and XGBoost clusters in Dataproc takes about 90 seconds.
https://gweb-cloudblog-publish.appspot.com/products/data-analytics/ml-with-xgboost-gets-faster-with-dataproc-on-gpus/amp/

#spark #machinelearning #xgboost #nvidia #gpu

❇️ @AI_Python_EN

article on handling railway disruptions with uncertain durations by a novel rolling-horizon two-stage stochastic method.

https://www.sciencedirect.com/science/article/pii/S2210970619300794?via%3Dihub

❇️ @AI_Python_EN