- Cologne, Germany
- linkedin.com/in/oleg-filatov/
Highlights
- Pro
Stars
Distributed Spectral Conditioned Optimizer for Muon/Scion.
H-Net: Hierarchical Network with Dynamic Chunking
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
An implementation of PSGD Kron second-order optimizer for PyTorch
A PyTorch native platform for training generative AI models
[ICLR 2026] Polynomial, trigonometric, and tropical activations
An "awesome music theory" kinda wiki with books, resources and courses for studying everything about music and sound
A flexible template, as a quick setup for deep learning projects in pytorch-lightning
YSDA course in Natural Language Processing
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
Collection of audio-focused loss functions in PyTorch
Deep Learning Audio Course, 2024
https://huyenchip.com/ml-interviews-book/
Source for https://fullstackdeeplearning.com
FFCV: Fast Forward Computer Vision (and other ML workloads!)
Official implementation of "Particle Transformer for Jet Tagging".
Free MLOps course from DataTalks.Club
Data science interview questions and answers
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.