Source: Алгоритмы машинного обучения

← Rendered

markdown source:

---
description: Список заметок о различных алгоритмах машинного обучения
category: list
title: Алгоритмы машинного обучения
tags: machine-learning
---
- [ml_monorepo](https://github.com/timothyyu/ml_monorepo) Super-monorepo for machine learning and algorithmic trading
- [CS50’s Introduction to Computer Science](https://cs50.harvard.edu/x/2023/)

## Data engines

- [[numpy]]
- [[pandas]]
- [missingno](https://github.com/ResidentMario/missingno) Missing data visualization module for Python.
- [[scipy]]
- [[pytorch]]

## [[computer-visions]]

- [[PIL]]
- [[imagehash]]
- [[diffusers]]

## NLP

- [Natural Language Toolkit](https://www.nltk.org/index.html) NLTK is a leading platform for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning, wrappers for industrial-strength NLP libraries, and an active discussion forum.
- [Levenshtein](https://rapidfuzz.github.io/Levenshtein/) a C extension module for fast computation of Levenshtein (edit) distance and edit sequence manipulation, string similarity, approximate median strings, and generally string averaging, string sequence and set similarity.
- [python-string-similarity](https://pypi.org/project/strsimpy/#levenshtein) a library implementing different string similarity and distance measures. A dozen of algorithms (including Levenshtein edit distance and sibblings, Jaro-Winkler, Longest Common Subsequence, cosine similarity etc.) are currently implemented.
- [open-llms](https://github.com/eugeneyan/open-llms) a list of open LLMs available for commercial use.

## [[graphs]]

## [[knowledge-graphs]]

## [[evolution-methods]]

## [[reinforcement-learning]]

## Boosting

- [[lightgbm]]
- [[lightgbm-parameters-tuning]]

## Recomendation systems

- [Re-play](https://sberbank-ai-lab.github.io/RePlay/)

## Preprocessing

- [scikit-lego](https://scikit-lego.readthedocs.io/en/latest/index.html) custom sxcikit-learn transformers, metrics and models

## Mining

- [siuba](https://siuba.readthedocs.io/en/latest/intro.html) is a tool for concise, flexible data-analysis over multiple data sources. It currently supports pandas DataFrames and SQL tables.

## Experiments piplines and deployments

- [sacred](https://github.com/IDSIA/sacred) is a tool to help you configure, organize, log and reproduce experiments
- [kedro](https://github.com/kedro-org/kedro) is an open-source Python framework for creating reproducible, maintainable and modular data science code
- [MLflow](https://mlflow.org/docs/latest/index.html) is an open source platform for managing the end-to-end machine learning lifecycle
- [AutoDeploy](https://github.com/kartik4949/AutoDeploy) allows configuration based MLOps
- [spacy](https://spacy.io/) train, manage, package, deploy nlp-models pipline
- [MLFlow](https://github.com/mlflow/mlflow/) Machine Learning Lifecycle Platform
- [KubeFlow](https://github.com/kubeflow/kubeflow) the cloud-native platform for machine learning operations - pipelines, training and deployment
- [RayWorkflow](https://github.com/ray-project/ray) provides a simple, universal API for building distributed applications, [дока](https://docs.ray.io/en/latest/workflows/concepts.html)
- [seldon-core](https://github.com/SeldonIO/seldon-core) converts your ML models (Tensorflow, Pytorch, H2o, etc.) or language wrappers (Python, Java, etc.) into production REST/GRPC microservices.
- [[jina]] Фреймворк для работы с ml-моделями
- [[docarray]] is a library for nested, unstructured data in transit, including text, image, audio, video, 3D mesh, etc.

## Neural networks

- [The Unreasonable Effectiveness of Recurrent Neural Networks](http://karpathy.github.io/2015/05/21/rnn-effectiveness/) статья

## Spiking NN

- [SnnTorch](https://github.com/jeshraghian/snntorch) Deep and online learning with spiking neural networks in Python

## Ready engines and models

- [EasyOCR](https://github.com/JaidedAI/EasyOCR) Ready-to-use OCR with 80+ supported languages and all popular writing scripts including: Latin, Chinese, Arabic, Devanagari, Cyrillic, etc.
- [Face Recognition](https://github.com/ageitgey/face_recognition) Recognize and manipulate faces from Python or from the command line with the world's simplest face recognition library.
- [Weights and biaces](https://wandb.ai/site/papers) Developer tools for machine learning gui

## Datasets

- [Recipe1M+](http://pic2recipe.csail.mit.edu/): A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images
- [Национальный корпус русского языка](https://ruscorpora.ru/) comertial license
- [pencorpora.org](http://opencorpora.org/) Открытый корпус


[numpy]: ../notes/numpy "Numpy"
[pandas]: ../notes/pandas "Pandas"
[scipy]: ../notes/scipy "Scipy"
[pytorch]: ../notes/pytorch "Machine learning framework pytorch"
[computer-visions]: computer-visions "Computer visions"
[PIL]: ../notes/PIL "Pillow - обработка изображений"
[imagehash]: ../notes/imagehash "imagehash - хеширование изображений"
[diffusers]: ../notes/diffusers "Diffusers library"
[graphs]: graphs "Machine learning with graphs"
[knowledge-graphs]: knowledge-graphs "Knowledge graphs"
[evolution-methods]: evolution-methods "Evolution methods"
[reinforcement-learning]: reinforcement-learning "Reinforcement learning"
[lightgbm]: ../notes/lightgbm "Lightgbm"
[lightgbm-parameters-tuning]: ../notes/lightgbm-parameters-tuning "Lightgbm parameters tuning"
[jina]: ../notes/jina "Jina"
[docarray]: ../notes/docarray "Docarray python"