Articles by Dmytro Spodarets
159 items
Data Phoenix Digest - ISSUE 46
We are excited to get back to work, to revive Data Phoenix from the ashes of war. Today you will know about emerging architectures for modern data infrastructure, backpropagation in RNN, masked generative image transformer, scalable large scene neural view synthesis, and more.
Apr 27, 2022
Data Phoenix Digest - #SupportUkraine
Dear Readers, Today our issue is dedicated to the war that Russia started against Ukraine. As you may know, on February 24, Russia started the full-scale war against Ukraine. We can and have to stop Russia from causing catastrophic damage to Ukraine and the whole world. Because they won't stop! They are shelling and bombing not only military infrastructure (as Russian propaganda claims) but civilians as well: schools, apartment buildings, kindergartens, hospitals, etc. Down below you can see h
Feb 27, 2022
Data Phoenix Digest - ISSUE 45
Calculating derivatives in PyTorch, automate your ML development pipeline with PyCaret, a video restoration transformer, adapting CV models for time series and automated EEG review, DALL-Eval, EvoJAX, and more ...
Feb 21, 2022![Data Science and Machine Learning from Scratch [And More]](https://assets.dataphoenix.info/uploads/media/9e15b73bb2b08607/data_phoenix_articles_4-min.png)
Data Science and Machine Learning from Scratch [And More]
We believe that any data scientist and ML professional should never stop learning. In this post, we provide an overview of the best resources and courses you can use to start digging in.
Feb 21, 2022
Data Phoenix Digest - ISSUE 44
Kubeflow pipeline from scratch, financial text classification using FinBERT, a single model for many visual modalities, a gentle introduction to supervised learning, GAN-based facial editing of real videos, NN-SVG, GreaseLM, Data2vec, videos, and more ...
Feb 14, 2022
Overview of the TOP Algorithms for Machine Learning. Part 2
Hi again! In the first part [https://dataphoenix.info/overview-of-the-top-algorithms-for-machine-learning-part-1/] of the article, we have covered Machine Learning tasks (Supervised, Unsupervised, and Reinforcement Learning) and such algorithms as Linear Regression, K-Nearest Neighbors (kNN), Convolutional Neural Network (CNN). In Part 2, we will review common methods of statistical analysis. But, to begin with, let’s figure out what exactly data analysis is. What Is Data Analysis? Data analys
Feb 12, 2022
Data Phoenix Digest - ISSUE 43
How to process a dataframe with millions of rows in seconds, calculating derivatives in PyTorch, BERT’s cousin for advanced topic modeling, understanding DBSCAN, convolutional Xformers for vision, transformers in medical imaging, UniFormer, HumanNeRF, Stanford CoreNLP, podcasts, and more ...
Feb 7, 2022
Data Phoenix Digest - ISSUE 42
Human-like AI avatars by DeepBrain AI, two-dimensional tensors in Pytorch, Unsupervised Reinforcement Learning benchmark, instant neural graphics primitives with a multiresolution hash encoding, a ConvNet for the 2020s, LaMDA, Plenoxel, NeROIC, courses, podcasts, and more ...
Jan 31, 2022
Data Phoenix Digest - ISSUE 41
Overview of the TOP algorithms for ML, distributed training, capacity recommendation engine, time series anomaly detection with PyFBAD, linear algebra with transformers, a ConvNet for the 2020s, JoJoGAN, Plenoxels, videos, courses, jobs, and more ...
Jan 21, 2022Data Phoenix Digest - ISSUE 40
Data Phoenix invites everyone to Slack chat, the birth of Albumentations, neural network from scratch, Self-Supervised Learning from 100 million medical images, a general language assistant as a laboratory for alignment, NL-Augmenter, projects, jobs, and more ...
Jan 14, 2022
Overview of the TOP Algorithms for Machine Learning. Part 1
In the first part of the article, we’ll talk about Machine Learning tasks (Supervised, Unsupervised, and Reinforcement Learning) and such algorithms as Linear Regression, K-Nearest Neighbors (kNN), Convolutional Neural Network (CNN). All algorithms are accompanied with examples of code that you play with on your own. Before we start reviewing the top ML algorithms, though, let’s first describe and define supervised, unsupervised and reinforced learning tasks, and learn how to differentiate them
Jan 13, 2022
The birth of Albumentations
I would like to talk about Albumentations, an open-source library for image Augmentations. An explanation of how it was born and evolved over time. The text’s primary purpose is to depict its creation, as I would like to have a story to enjoy in 20 years. I will mainly talk about the library’s origins and cover the process of iterative improvements in fewer details. The text could be more concise, but I prefer to keep unnecessary information for historical purposes. Albumentations [https://alb
Jan 7, 2022