tomgeorge1234 Goto Github PK
Name: Tom George
Type: User
Bio: UCL Neuroscience and Machine Learning
Twitter: TomNotGeorge
Name: Tom George
Type: User
Bio: UCL Neuroscience and Machine Learning
Twitter: TomNotGeorge
Extended pickling support for Python objects
We use deep convolutional neural networks to solve a classic oceanographic problem: how to predict heat fluxes in turbulent flows given only readily available surface information.
A colab-style DL tutorial for how to build and train DNNs (with and without autograd packages) from scratch.
Makes gp videos for Joels project
Modelling hippocampus as a Helmholtz machine
A colab-style tutorial for how to build Hopfield Networks (classic and modern) and train them to memorise patterns and flags
Notebook demonstration of basic RSA approaches to explore representational structure in 1p calcium imaging data
A colab-style tutorial for how to model spatial behaviour and spatial representations using the RatInABox simulation toolkit.
A colab-style tutorial on neuro-reinforcement learning
Code and data for my Part III Masters Project, University of Cambridge. This project looks at using variational autoencoders on Ovarian Cancer datasets to investigate methods of discovering gene signatures responsible for causing platinum resistance.
Neyman-Scott point process model to identify sequential firing patterns in high-dimensional spike trains
Code and pipeline for pupillometry. Produced for PhD rotation in Akrami lab, for studying implicit statistical learning in humans performing a gap detection task. Code should be adaptable for more general pupillometry projects.
State space models for decoding hippocampal trajectories and determining their type using sorted or clusterless data
Code for computing with reservoir nets, pairs of mutually supervising reservoir nets and training with FORCE learning. Produced for PhD rotation in Akrami Lab studying temporal structure learning.
Basic statistics for Julia
We study place and grid cells of an RL agent learns successor representations (SR) in compositional mazes.
Code for my paper: "Theta sequences as eligibility traces: a biological solution to credit assignment"
Simulation code (python) and report for a study into the close approach of two multi-star galaxies and the subsequent formation of tidal tails from the extreme self generated tidal forces present.
I am Tom George and this is my website
A package I wrote for formatting and saving figures with matplotlib
TReND school in Comp Neuro and ML
Here I use pytorch to understand what drives neuronal selective in deep neural networks trained to perform multiple tasks simultaneously
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.