snakers41

All these things will be lost like tears in rain.

1 / 74

Nov 20, 18

Nov 20, 18

Feb 9, 17

Winning a CFT 2018 spelling correction competition

Building a task-agnostic seq2seq pipeline on a challenging domain

Posted by snakers41 on November 20, 2018

Deep learning Natural Language Processing

Building client routing / semantic search and clustering arbitrary external corpuses at Profi.ru

And some applied benchmarks of sentence embedding methods

Posted by snakers41 on November 2, 2018

Deep learning Natural Language Processing

Parsing Common Crawl in 4 plain scripts in python

(alas not 2) =)

Posted by snakers41 on October 8, 2018

Deep learning Natural Language Processing

Parsing Common Crawl in 2 plain scripts in python

So easy! Really!

Posted by snakers41 on October 4, 2018

Deep learning Natural Language Processing

Parsing Wikipedia in 4 simple commands for plain NLP corpus retrieval

Really?

Posted by snakers41 on October 3, 2018

Deep learning Natural Language Processing

Training your own MNASNET

Or how we failed

Posted by snakers41 on September 3, 2018

Neural networks Computer vision Deep learning ML and CV competitions Data Science

Speeding up word distance calculation 100x

My plain approach to faster and more practical cosine distance calculation

Posted by snakers41 on August 12, 2018

Deep learning ML and CV competitions Data Science

Solving class imbalance on Google open images

Or potentially building a model cascade to alleviate severe class imbalance

Posted by snakers41 on July 23, 2018

Neural networks Computer vision Deep learning ML and CV competitions Data Science

Playing with Crowd-AI mapping challenge - or how to improve your CNN performance with self-supervised techniques

A small case for searching for internal structure within the data, weighting and training your CNNs properly

Posted by snakers41 on July 15, 2018

Neural networks Computer vision Deep learning ML and CV competitions Data Science

Playing with Variational Auto Encoders - PCA vs. UMAP vs. VAE on FMNIST / MNIST

TLDR - they are very cool - but useful only on very simple domains and datasets

Posted by snakers41 on July 7, 2018

Neural networks Computer vision Deep learning ML and CV competitions Data Science