Git Product home page Git Product logo

jakelevi1996's Projects

backprop2 icon backprop2

Investigating data-efficiency for MNIST using meta-learning, and also investigating modified 2nd-order training methods

comp-neuro icon comp-neuro

Computational neuroscience simulations including TD reinforcement learning, Hopfield networks, and cortical circuit dynamics

constructions icon constructions

Iteratively create and display constructions in Euclidean space

gaussian-processes icon gaussian-processes

This repository is primarily for coursework submission to 4F13: 'Probabilistic machine learning' coursework 1.

jutility icon jutility

Collection of Python utilities intended to be useful for machine learning research and experiments

mapreduce-meta-learning icon mapreduce-meta-learning

This repository implements meta-learning algorithms from the literature such as Reptile (Nichol, 2018) as a map-reduce algorithm.

newtons-method icon newtons-method

Implementation and research on generalisations of Newton's method for optimisation

nns icon nns

Personal MATLAB implementation of artificial neural network training

norm-minimisation icon norm-minimisation

Find solutions to L1, L2 and Linf norm-minimisation problems using approximate gradient-based approaches and compare with exact least-squares and linear-programming methods

notes icon notes

My notes on everything (WIP)

probabilistic-ranking icon probabilistic-ranking

This repository is primarily for coursework submission to 4F13: 'Probabilistic machine learning' coursework 2.

reinforcement_learning icon reinforcement_learning

Repository containing implementations of RL (reinforcement learning) algorithms, specifically from "Sutton, Richard S., and Andrew G. Barto. Reinforcement learning: An introduction. MIT press, 2018." Eventually I hope to also add implementations of more cutting edge RL algorithms directly from the literature.

robotic-simulation icon robotic-simulation

This repository is primarily for coursework submission to 4M20: 'Robotics' coursework 1.

roxel icon roxel

Investigation into perception of shapes from motion

stochastic-optimisation icon stochastic-optimisation

Some stochastic optimisation algorithms (Tabu search and Particle Swarm Optimisation), tested and compared on the 2D and 5D Schwefel functions

text-gif icon text-gif

Make GIF of given text file, letter by letter or word by word

tf.app.run-test icon tf.app.run-test

Test repository for calling the tf.app.run wrapper from a different script

threading-test icon threading-test

Test repository for running a list of jobs in Python using threads

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.