Machine Learning World

24 tutorials with datasets https://www.analyticsvidhya.com/blog/2018/05/24-ultimate-data-science-projects-to-boost-your-knowledge-and-skills/?utm_source=facebook.com&utm_medium=social&fbclid=IwAR0xFMjCqgAsKloDOL2qffjg7eQL0XOeYycDLE7YSa44Qji4Bk9UCyZtlO0

Analytics Vidhya

Top 30 Machine Learning Projects for Beginners in 2025

Explore 30 Machine Learning Projects for beginners to advanced levels, enhancing skills in regression, classification, and deep learning.

5.72K viewsAndrey Nikishaev, 08:56

Machine Learning World

Interesting view on object detection https://arxiv.org/abs/1904.01355

arXiv.org

FCOS: Fully Convolutional One-Stage Object Detection

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object...

5.03K viewsAndrey Nikishaev, 20:03

Machine Learning World

Привет. Сейчас в Киеве в Rails Reactor выступает Алексей Григорьев, и рассказывает о том как OLX Group (Berlin) детектит дубликаты контента. Подключайтесь к стриму с AI Tonight #6 https://www.facebook.com/RailsReactor/videos/390499905004729

Facebook Watch

Rails Reactor

Rails Reactor is live now.

5.46K viewsAndrey Nikishaev, 16:52

Machine Learning World

Nice! https://github.com/huggingface/pytorch-transformers

GitHub

GitHub - huggingface/transformers: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models…

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. - GitHub - huggingface/t...

3.8K viewsAndrey Nikishaev, 15:47

Machine Learning World

The Ai4 conference series hosts AI & ML events across Finance, Healthcare, Retail, Cybersecurity, and more. ML World Telegram members can use the special code COMMUNITY20 for a *20% discount* on your pass! Check it out 👉 https://bit.ly/Ai-4-ML-World

Ai4

Artificial Intelligence Conference

4.24K viewsAndrey Nikishaev, 12:25

Machine Learning World

Multitask learning network https://github.com/subho406/OmniNet

GitHub

GitHub - subho406/OmniNet: Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning"…

Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain - GitHub - ...

4.84K viewsAndrey Nikishaev, 18:48

Machine Learning World

Good free course on ray-tracing, can be useful for those who want s to work in 3d area
https://www.youtube.com/playlist?list=PLujxSBD-JXgnGmsn7gEyN28P1DnRZG7qi

4.72K viewsAndrey Nikishaev, 07:29

Machine Learning World

Interesting paper on fast image generation https://arxiv.org/pdf/1906.00446.pdf

3.74K viewsAndrey Nikishaev, 20:07

Machine Learning World

New State of the Art in Semantic Segmentation https://arxiv.org/abs/1907.05740

4.95K viewsAndrey Nikishaev, 16:14

Machine Learning World

As all you know our channel spend all money from avertisment on supporting homeless animals. Yesterday we start helping this cat https://www.facebook.com/anikishaev/posts/2331822493561951 (photo 18+)
He was injured quite badly, but after surgery he is doing ok. Question with money fully closed and only thing that we need is a new home and loving family for him.
So if any of u want to help and get new fluffy friend then write me on [email protected]
Also i'll be very gratefull for sharing this with your friends.

Facebook

Andrey Nikishaev

Котейку прооперировали, отходит от наркоза. Состояние стабильное. Передержку нашли. Как оклемается будем делать наверно пластику, сейчас узнаю на этот счет. Бедный малыш пережил настоящий ад, лично...

3.6K viewsAndrey Nikishaev, 11:10

Machine Learning World

https://arxiv.org/abs/1907.10949

arXiv.org

Y-Autoencoders: disentangling latent representations via...

In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs)....

3.19K viewsAndrey Nikishaev, 06:24

Machine Learning World

https://arxiv.org/abs/1907.11111

arXiv.org

MultiDepth: Single-Image Depth Estimation via Multi-Task...

We introduce MultiDepth, a novel training strategy and convolutional neural
network (CNN) architecture that allows approaching single-image depth
estimation (SIDE) as a multi-task problem. SIDE is...

3.3K viewsAndrey Nikishaev, 06:25

Machine Learning World

https://heartbeat.fritz.ai/a-2019-guide-to-semantic-segmentation-ca8242f5a7fc

Fritz ai

A 2019 Guide to Semantic Segmentation - Fritz ai

Semantic segmentation refers to the process of linking each pixel in an image to a class label. These labels could include a person, car, flower, piece of furniture, etc., just to mention a few. We can think of semantic segmentation… Continue reading A 2019…

3.64K viewsAndrey Nikishaev, 06:26

Machine Learning World

Machine Learning World pinned «As all you know our channel spend all money from avertisment on supporting homeless animals. Yesterday we start helping this cat https://www.facebook.com/anikishaev/posts/2331822493561951 (photo 18+) He was injured quite badly, but after surgery he is doing…»

07:32

Machine Learning World

Good article on basic of linear regresions(russian) https://m.habr.com/ru/company/ods/blog/322076/

Хабр

Базовые принципы машинного обучения на примере линейной регрессии

Здравствуйте, коллеги! Это блог открытой русскоговорящей дата саентологической ложи . Нас уже легион, точнее 2500+ человек в слаке. За полтора года мы нагенерили 800к+ сообщений (ради этого слак...

3.98K viewsAndrey Nikishaev, 10:08

Machine Learning World

If you didn't know, there is a collection of datasets, ready to use with TF
https://github.com/tensorflow/datasets

GitHub

GitHub - tensorflow/datasets: TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ... - tensorflow/datasets

3.88K viewsAndrey Nikishaev, 10:57

Machine Learning World

Good article on BERT architecture
https://towardsdatascience.com/breaking-bert-down-430461f60efb

Medium

Breaking BERT Down

What is BERT?

4.31K viewsAndrey Nikishaev, 10:45

Machine Learning World

New era of float operations (russian)
https://habr.com/ru/post/462385/

Хабр

Новый подход может помочь нам избавиться от вычислений с плавающей запятой

В 1985 году Институт инженеров электротехники и электроники (IEEE) установил стандарт IEEE 754, отвечающий за форматы чисел с плавающей запятой и арифметики, к...

3.67K viewsAndrey Nikishaev, 20:02

Machine Learning World

Reimplemented HDRNet model aka Deep Bilateral Learning for Real-Time Image Enhancements in PyTorch
https://github.com/creotiv/hdrnet-pytorch

Now you dont need to fuck you brain off compiling cuda operations in TF, and on my machine it works even faster then original implementation

GitHub

GitHub - creotiv/hdrnet-pytorch: Unofficial PyTorch implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement'…

Unofficial PyTorch implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017 https://groups.csail.mit.edu/graphics/hdrnet/ - creotiv/hdrnet-pytorch

3.48K viewsAndrey Nikishaev, 09:46

Machine Learning World

Awesome python wrapper for RANSAC
Examples:
https://github.com/ducha-aiki/pyransac/blob/master/examples/how-to-use-detailed.ipynb

GitHub

pyransac/examples/how-to-use-detailed.ipynb at master · ducha-aiki/pyransac

Fast and accurate python RANSAC with LO, LAF-check - ducha-aiki/pyransac

3.38K viewsAndrey Nikishaev, 17:31

Machine Learning World

That's fucken awesome result of Video Style Transfer https://dcgi.fel.cvut.cz/home/sykorad/ebsynth.html