Sergei Bykov (SergeiDBykov)

SergeiDBykov

Geek Repo

Company:Max Planck Institute For Astrophysics

Location:Munich

Github PK Tool:Github PK Tool

Sergei Bykov's starred repositories

coding-interview-university

A complete computer science study plan to become a software engineer.

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Language:PythonLicense:MITStargazers:53101Issues:444Issues:131

privateGPT

Interact with your documents using the power of GPT, 100% privately, no data leaks

Language:PythonLicense:Apache-2.0Stargazers:49730Issues:443Issues:992

shap

A game theoretic approach to explain the output of any machine learning model.

Language:Jupyter NotebookLicense:MITStargazers:22339Issues:238Issues:2518

localGPT

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

Language:PythonLicense:Apache-2.0Stargazers:19733Issues:167Issues:535

prophet

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

Language:PythonLicense:MITStargazers:18205Issues:450Issues:2138

deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

Language:Jupyter NotebookLicense:MITStargazers:18128Issues:647Issues:184

neural-networks-and-deep-learning

Code samples for my book "Neural Networks and Deep Learning"

Language:PythonStargazers:15810Issues:1095Issues:0

pandas-ai

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

Language:PythonLicense:NOASSERTIONStargazers:12395Issues:102Issues:665

darts

A python library for user-friendly forecasting and anomaly detection on time series.

Language:PythonLicense:Apache-2.0Stargazers:7827Issues:59Issues:1508

ml-interviews-book

https://huyenchip.com/ml-interviews-book/

sketch

AI code-writing assistant that understands data content

Language:PythonLicense:MITStargazers:2219Issues:18Issues:25

astroML

Machine learning, statistics, and data mining for astronomy and astrophysics

Language:PythonLicense:BSD-2-ClauseStargazers:1042Issues:96Issues:156

astroquery

Functions and classes to access online data resources. Maintainers: @keflavich and @bsipocz and @ceb8

Language:PythonLicense:BSD-3-ClauseStargazers:695Issues:30Issues:1360

gpubootcamp

This repository consists for gpu bootcamp material for HPC and AI

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:503Issues:23Issues:62

ml-in-cosmology

A comprehensive list of published machine learning applications to cosmology

iminuit

Jupyter-friendly Python interface for C++ MINUIT2

Language:PythonLicense:NOASSERTIONStargazers:280Issues:16Issues:325

astronomy-to-data-science

resources for transitioning from academic astronomy to industry data science

nway

nway -- Bayesian cross-matching of astronomical catalogues

Language:PythonLicense:NOASSERTIONStargazers:54Issues:9Issues:22

BXA

Bayesian X-ray analysis (nested sampling for Xspec and Sherpa)

Language:PythonLicense:GPL-3.0Stargazers:53Issues:8Issues:44

scinum

Scientific numbers with multiple uncertainties, correlation-aware gaussian error propagation and numpy support.

Language:PythonLicense:BSD-3-ClauseStargazers:26Issues:3Issues:10

ztf-viewer

ZTF data releases light curve viewer

Language:PythonLicense:MITStargazers:14Issues:4Issues:157

RainbowLasso

RainbowLasso compiles matched aperture fluxes from ultraviolet to infrared for all-sky surveys.

Language:MakefileLicense:AGPL-3.0Stargazers:4Issues:3Issues:0

Hyper-parameter_optimization_for_Random_Forest

In this repository we optimize the random forest (RF) hyper-parameters for the dataset; DR16 cross-matched with the WISE catalogue. In this case, we trained the algorithms on about 80% of the dataset to find the best parameter settings for the algorithms to best estimate the photometric redshifts using the sk-learn RandomisedSearchCV. We used the "neg_mean_squared_error", "neg_median_absolute_deviation" and both "neg_mean_squared_error" and "neg_median_absolute_deviation" as a scoring metrics. The "neg_median_absolute_deviation" yields best results for this project.

Language:Jupyter NotebookStargazers:3Issues:1Issues:0

kaggle-munich

the notebook for Kaggle Munich SHAP 101 talk

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:3Issues:2Issues:0

watchbot

Implementation of the watchbot, to control the behaviour of a LLM-based chatbot

Language:PythonLicense:MITStargazers:2Issues:0Issues:0

planck_szcat

Planck U-Net and y-map SZ catalogs

Language:Jupyter NotebookStargazers:1Issues:0Issues:0

ai_projects

AI related projects -- learning progress

Language:Jupyter NotebookStargazers:1Issues:0Issues:0
Language:Jupyter NotebookStargazers:1Issues:1Issues:0