Open in app
Sign inGet started
The Super-Impatient’s Guide to Getting Started with Bort

The Super-Impatient’s Guide to Getting Started with Bort

“We tested Bort on 23 NLU tasks, and on 20 of them, it improved on BERT’s performance — by 31% in one case — even though it’s 16% the size…
Go to the profile of Cees Roele
Cees Roele
A minimal, production-ready, NN-based recommender system

A minimal, production-ready, NN-based recommender system

Some time ago I wrote about the surprizingly good performance of a really simple autoencoder-based recommender build with keras and R as…
Go to the profile of dimalvovs
dimalvovs
Textual data augmentation with back-translation

Textual data augmentation with back-translation

Improve performance of your NLP models by a powerful data augmentation technique
Go to the profile of Dmitry Yemelyanov
Dmitry Yemelyanov
TensorFlow model deployment options

TensorFlow model deployment options

Learn three major TensorFlow deployment options available, their strong sides and weaknesses!
Go to the profile of Dmitry Yemelyanov
Dmitry Yemelyanov
Dimensionality Reduction with t-SNE

Dimensionality Reduction with t-SNE

Browsing 300D word embeddings through the 2D lens
Go to the profile of Dmitry Yemelyanov
Dmitry Yemelyanov
Word Embeddings by example

Word Embeddings by example

A gentle introduction to the word embeddings, key concept of Natural Language Processing.
Go to the profile of Dmitry Yemelyanov
Dmitry Yemelyanov
Learn Heteroskedasticity in 2 minutes

Learn Heteroskedasticity in 2 minutes

Complex term explained with simple words
Go to the profile of Dmitry Yemelyanov
Dmitry Yemelyanov
5 minutes on predictive model monitoring on the data censored by itself

5 minutes on predictive model monitoring on the data censored by itself

At work I and my team build pipelines that create and deploy machine learning (ML) models. Very often these models are used to estimate…
Go to the profile of dimalvovs
dimalvovs
We asked AI what it thinks about the Baltics and this is what happened…

We asked AI what it thinks about the Baltics and this is what happened…

Catching up with new developments in the field of Machine Learning could be a full-time job in itself. When it comes to the Natural…
Go to the profile of Kate Kuznecova
Kate Kuznecova
Security Data Science: Analysis of Windows Event Logs using pandas DataFrame

Security Data Science: Analysis of Windows Event Logs using pandas DataFrame

Transform XML into DataFrame, and as example identify malware Command & Control channel using statistics and visualisation.
Go to the profile of Dmitrijs Trizna
Dmitrijs Trizna
About Riga Data Science ClubLatest StoriesArchiveAbout MediumTermsPrivacyTeams