Giter VIP home page Giter VIP logo

Mathias Oliver Valdbjørn Rønnelund's Projects

adventofcode icon adventofcode

After having participated for 2 years semi efficient, I will try this year to be more consisten with Advent of Code

eldenringai icon eldenringai

An AI that currently is in beta, but will potentially move the character around based on facial features

hyperparametersmnist icon hyperparametersmnist

Machine Learning has been a popular topic of research for the last several decades. The field of machine learning is notorious for the large amount of parameters which can be tuned, in order to provide better results. For this assignment we will be training artificial neural networks for image classification. We will focus on the impact of different batch sizes when training on a modern system with consumer-grade GPUs, and how different batch sizes affect the accuracy of various models. For our benchmarks, we will be using the MNIST dataset, which consists of 70.000, 28x28 gray scale images of hand-written digits, 0-9.\footnote{\url{http://yann.lecun.com/exdb/mnist/}} The dataset has a total uncompressed size of 54 MB. We will also be exploring different types of deep learning models with varying complexity, namely a fully connected network, a convolutional network (CNN), and a Residual Network (ResNet). Furthermore, we will be exploring the impacts on throughput and accuracy when training on one or on several high-end consumer-grade GPUs.

images2minecraft icon images2minecraft

In this particular project, we turned a 2D Image into Minecraft pixel art and then scaled it in 3D such that it became possible to live in it. An actual Minecraft House.

kattis icon kattis

Kattis Task (old solution have been lost on itu's github)

osm_map_parser icon osm_map_parser

A larger project made in Java. The project was based around creating a live map of Denmark with the assistanse of a KD_Tree

pyweek30 icon pyweek30

For this pyweek 30 the focus will be on "castaway". The majority of the idea will be based on an idle clicker game

qdeeplearning icon qdeeplearning

A trial to start learning how the openAI library works and how to develop Q ai algorithms

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.