SVM. Объяснение с нуля, имплементация и подробный разбор
https://habr.com/ru/company/ods/blog/484148/
https://habr.com/ru/company/ods/blog/484148/
Хабр
SVM. Подробный разбор метода опорных векторов, реализация на python
Привет всем, кто выбрал путь ML-самурая! Введение: В данной статье рассмотрим метод опорных векторов ( англ. SVM, Support Vector Machine ) для задачи классификации. Будет представлена основная идея...
Microsoft open sources breakthrough optimizations for transformer inference on GPU and CPU
https://cloudblogs.microsoft.com/opensource/2020/01/21/microsoft-onnx-open-source-optimizations-transformer-inference-gpu-cpu/
https://cloudblogs.microsoft.com/opensource/2020/01/21/microsoft-onnx-open-source-optimizations-transformer-inference-gpu-cpu/
Microsoft Open Source Blog
Microsoft open sources breakthrough optimizations for transformer inference on GPU and CPU
Microsoft has open sourced enhanced versions of transformer inference optimizations into the ONNX Runtime and extended them to work on both GPU and CPU.
Creating Python Functions for Exploratory Data Analysis and Data Cleaning
https://towardsdatascience.com/creating-python-functions-for-exploratory-data-analysis-and-data-cleaning-2c462961bd71
https://towardsdatascience.com/creating-python-functions-for-exploratory-data-analysis-and-data-cleaning-2c462961bd71
Medium
Creating Python Functions for Exploratory Data Analysis and Data Cleaning
Exploratory Data Analysis and Data Cleaning are two essential steps before we start to develop Machine Learning Models, and they can be…
PyTorch3d is FAIR's library of reusable components for deep learning with 3D data.
https://github.com/facebookresearch/pytorch3d
https://github.com/facebookresearch/pytorch3d
GitHub
GitHub - facebookresearch/pytorch3d: PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data - facebookresearch/pytorch3d
NeurIPS 2019: тренды ML, которые будут с нами следующее десятилетие
https://habr.com/ru/company/sberbank/blog/485384/
https://habr.com/ru/company/sberbank/blog/485384/
Хабр
NeurIPS 2019: тренды ML, которые будут с нами следующее десятилетие
NeurIPS (Neural Information Processing Systems) – самая большая конференция в мире по машинному обучению и искусственному интеллекту и главное событие в мире dee...
Natural Language Processing Best Practices & Examples
https://github.com/microsoft/nlp-recipes
https://github.com/microsoft/nlp-recipes
GitHub
GitHub - microsoft/nlp-recipes: Natural Language Processing Best Practices & Examples
Natural Language Processing Best Practices & Examples - microsoft/nlp-recipes
Introducing Label Studio, a swiss army knife of data labeling
https://towardsdatascience.com/introducing-label-studio-a-swiss-army-knife-of-data-labeling-140c1be92881
https://towardsdatascience.com/introducing-label-studio-a-swiss-army-knife-of-data-labeling-140c1be92881
Medium
Introducing Label Studio, a swiss army knife of data labeling
Professional machine learning tools are both the foundation and scaffolding for building successful ML based products.
Визуализируя нейронный машинный перевод (seq2seq модели с механизмом внимания)
https://habr.com/ru/post/486158/
https://habr.com/ru/post/486158/
Хабр
Визуализируя нейронный машинный перевод (seq2seq модели с механизмом внимания)
Привет, Хабр! Представляю вашему вниманию перевод статьи "Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention)" автора Jay...
Transformers 2.4.0 is out 🤗
- Training transformers from scratch is now supported
- New models, including *FlauBERT*, Dutch BERT, *UmBERTo*
- Revamped documentation
- First multi-modal model, MMBT from @facebookai, text & images
Bye bye Python 2 🙃
https://t.co/16M3eqAIcy
- Training transformers from scratch is now supported
- New models, including *FlauBERT*, Dutch BERT, *UmBERTo*
- Revamped documentation
- First multi-modal model, MMBT from @facebookai, text & images
Bye bye Python 2 🙃
https://t.co/16M3eqAIcy
GitHub
Releases · huggingface/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. - huggingface/transformers
Открытый курс «Deep Learning in NLP» от создателей DeepPavlov на базе курса cs224n
https://habr.com/ru/company/ods/blog/487172/
https://habr.com/ru/company/ods/blog/487172/
Хабр
Материалы NLP курса от DeepPavlov
В этой статье вы найдете материалы очных курсов «Deep Learning in NLP», которые запускались командой DeepPavlov в 2018-2019 годах и которые являлись частичной адаптацией Stanford NLP course — cs224n ....
TyDi QA: A Multilingual Question Answering Benchmark
https://ai.googleblog.com/2020/02/tydi-qa-multilingual-question-answering.html?m=1
https://ai.googleblog.com/2020/02/tydi-qa-multilingual-question-answering.html?m=1
blog.research.google
TyDi QA: A Multilingual Question Answering Benchmark
BERT, ELMo, & GPT-2: How contextual are contextualized word representations?
https://kawine.github.io/blog/nlp/2020/02/03/contextual.html
https://kawine.github.io/blog/nlp/2020/02/03/contextual.html
Kawin Ethayarajh
BERT, ELMo, & GPT-2: How contextual are contextualized word representations?
Incorporating context into word embeddings - as exemplified by BERT, ELMo, and GPT-2 - has proven to be a watershed idea in NLP. Replacing static vectors (e.g., word2vec) with contextualized word representations has led to significant improvements on virtually…
5 New Features in pandas 1.0 You Should Know About
https://towardsdatascience.com/5-new-features-in-pandas-1-0-you-should-know-about-fc31c83e396b
https://towardsdatascience.com/5-new-features-in-pandas-1-0-you-should-know-about-fc31c83e396b
Medium
5 New Features in pandas 1.0 You Should Know About
Dynamic window functions, faster apply and more.
Natural Language Processing. Итоги 2019 и тренды на 2020
https://habr.com/ru/company/huawei/blog/487730/
https://habr.com/ru/company/huawei/blog/487730/
Хабр
Natural Language Processing. Итоги 2019 и тренды на 2020
Всем привет. С некоторым запозданием я решил опубликовать эту статью. Каждый год я стараюсь подвести итоги произошедшего в области обработки естественного языка (natural language processing). Не стал...
Growing Neural Cellular Automata
Differentiable Model of Morphogenesis
https://distill.pub/2020/growing-ca/
Differentiable Model of Morphogenesis
https://distill.pub/2020/growing-ca/
Distill
Growing Neural Cellular Automata
Training an end-to-end differentiable, self-organising cellular automata model of morphogenesis, able to both grow and regenerate specific patterns.