GithubHelp home page GithubHelp logo

Hello there!

I am a PhD student at the University of Cambridge (edit: thesis defended and looking for a job!). I work on deep learning with graph-structured data, mostly within biomedical contexts but also in many others! I like thinking about,and working with, complex and dynamic systems at various scales.

  • I am currently doing things with multi-omics data, relational deep learning, and networks for work/research. For fun, I am currently studying generative modelling and multi-agent systems.

  • šŸŒ± Iā€™m currently working on PyRelational, a one-stop shop for constructing active learning pipelines.

    • PyRelationAL supports:
      • Construction of complex active learning pipelines
      • Development of novel acquisition functions / strategies / batching methods
      • Works with all your favourite ML frameworks and none as well
      • Interfacing with other AL packages

  • I also work in a much less frequent manner on:

  • šŸ“« How to reach me:

Paul Scherer's Projects

networkx icon networkx

Official NetworkX source code repository.

paper-now icon paper-now

Create, edit and display a journal article, entirely in GitHub

projects icon projects

A list of practical projects that anyone can solve in any programming language.

protclus icon protclus

Python 3 library implementing a number of topological clustering techniques used on protein-protein interaction networks.

pytorch icon pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

reasteroids icon reasteroids

A remake of my previous Asteroids and Astral Tanks Game.

renpy icon renpy

The Ren'Py Visual Novel Engine

rubypractice icon rubypractice

Simple repository containing solutions to LRTHW so I can get some practice on the library computers, etc.

sdp icon sdp

Group 7: Lucky Number Seven

selpapp icon selpapp

Public repository of web application made during SELP, work will continue in Private repository.

simpleae icon simpleae

Simple minimal implementation of Autoencoders and variants. Useful for instruction in class.

simplegnn icon simplegnn

Pure Python/Numpy implementation of GNNs for expositional purposes.

simplemhvae icon simplemhvae

Simple one-off implementation of markovian hierarchical variational auto-encoders

simplenn icon simplenn

Simple neural network implementation using basic python for instruction in class

simplernn icon simplernn

Simple Python and Numpy implementations of RNNs. Based of Andrej Karpathy's work. For expositional purposes.

simplevae icon simplevae

Simple vanilla PyTorch implementation of a VAE, and several variants such as the MHVAE

slurms icon slurms

Some slurms useful for running python and executable scripts for CSD3

transformer icon transformer

Implementation of Transformer model (originally from Attention is All You Need) applied to Time Series.

usualsuspects icon usualsuspects

Personal tools for making visualisations and other figures that pop up in ML papers all the time.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    šŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. šŸ“ŠšŸ“ˆšŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ā¤ļø Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.