szemyd

fold

🪁 A fast Adaptive Machine Learning library for Time-Series, that lets you build, deploy and update composite models easily. An order of magnitude speed-up, combined with flexibility and rigour. This is an internal project - documentation is not updated anymore and substantially differ from the current API.

fold-wrappers

🧱 Wrappers for 3rd party models to be used with fold (https://github.com/dream-faster/fold)

krisi

⏳ Evaluation of Time-Series Predictions with powerful pdf and web Reporting. Tailored for evaluation of metrics over time!

classical-artificial-intelligence

Solutions for Classical Planning, Adversarial Search, Optimization, Probabilistic Models, with eg.: Monte Carlo Tree Search, Constrain Solvers.

deep-reinforcement-learning

DQN with Prioritized Experience Replay, DDPG for Continous Environments, DDPG for Multi-Agent Reinforcement Learning

deep-reinforcement-learning-nd

Repo for the Deep Reinforcement Learning Nanodegree program. Included: Value-based and Policy-based methods, Temporal Difference Methods, DQN with Prioritized Experience Replay, Multi-Agent Reinforcement Learning

genetic-algorithm-web

A Genetic Algorithm optimized for the web. Implemented in P5.js, it gives you the starter code to explore evolutionary optimization problems.

neuralnet-vga-analysis

Improving the speed of Visibility Graph Analysis by two orders of magnitude with the help of Neural Nets. This project was conducted as part of the Final Thesis for MSc Architectural Computation, Bartlett, University College London.

packaging-python

📦 This is a template repo on how to package a python project to be distributable.

python-api-example

🔌 This is an example project on how to configure and wrap a python app into Flask to provide api services.

szemyd/classical-artificial-intelligence

Solutions for Classical Planning, Adversarial Search, Optimization, Probabilistic Models, with eg.: Monte Carlo Tree Search, Constrain Solvers.

szemyd/deep-reinforcement-learning

DQN with Prioritized Experience Replay, DDPG for Continous Environments, DDPG for Multi-Agent Reinforcement Learning

szemyd/deep-reinforcement-learning-nd

Repo for the Deep Reinforcement Learning Nanodegree program. Included: Value-based and Policy-based methods, Temporal Difference Methods, DQN with Prioritized Experience Replay, Multi-Agent Reinforcement Learning

szemyd/genetic-algorithm-web

A Genetic Algorithm optimized for the web. Implemented in P5.js, it gives you the starter code to explore evolutionary optimization problems.

szemyd/neuralnet-vga-analysis

Improving the speed of Visibility Graph Analysis by two orders of magnitude with the help of Neural Nets. This project was conducted as part of the Final Thesis for MSc Architectural Computation, Bartlett, University College London.

szemyd/packaging-python

📦 This is a template repo on how to package a python project to be distributable.

szemyd/python-api-example

🔌 This is an example project on how to configure and wrap a python app into Flask to provide api services.

szemyd/streamlit-heroku-template

┉ Quick streamlit frontend that you can deploy to heroku

szemyd/CodeLSTM

szemyd/deep-reinforcement-learning2

Repo for the Deep Reinforcement Learning Nanodegree program

szemyd/dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

szemyd/dotenv

Loads environment variables from .env for nodejs projects.

szemyd/event_generator_ics

szemyd/gatsby-starter-hero-blog

szemyd/markdown-css-themes

A collection of css themes for Markdown

szemyd/morphogenetic-agent-segmentation

szemyd/morphogenetic-genetic-algorithm

szemyd/morphogenetic-nurb-surface

szemyd/packaging-python-public

szemyd/react-i18next

Internationalization for react done right. Using the i18next i18n ecosystem.

szemyd/React-Typescript-P5--Boilerplate

This is a boilerplate that let's you quickly start a React + Processing (P5.js) file with TypeScript preinstalled.

szemyd/research-neural-code-search

🔎 Finding the correct Stackoverflow answer for each code snippet

szemyd/sphinx-doc

szemyd/webparam

Created with CodeSandbox