Anđela Todorović's Projects
Tbilisi State University workshop - notebook & slides
Manipulations with basic geometrical primitives, such as point, line, plane, sphere, triangle in 3D space
Manipulations with basic geometrical primitives, such as point, line, plane, sphere, triangle in 3D space: translation and rotation operations, distance calculation, intersections, orthogonal projections of one object into another, etc. The objects can be defined in global or in one of the local coordinate systems and converted form one coordinate system into another. The library was build to be as simple and intuitive as posible. Users do not have to remember the reference coordinate system of each object. The objects store the coordinate system they are defined in and all transformations will be caried out implicitly when necessary.
My implementation of the Gibbs Sampler on NVIDIA Jetson Nano
A swift based library for IOS/OSX GPU Machine and Deep Learning for Kaggle
My solution to DrivenData competition Machine Learning with a Heart. Beat the benchmark and currently rated 90/2190.
Classifing images from the CIFAR-10 dataset. The images need to be normalized and the labels need to be one-hot encoded, them inserted into the convolutional network with convolutional, max pooling, dropout, and fully connected layers.
Programming assignments from the course Introduction to Deep Learning, by National Research University Higher School of Economics
Configuration scripts and install guides for NVIDIA Jetson platform
Some of the programming assignments in Linear Algebra, as far as some lecture scripts.
My solutions to the complete Machine Learning Course by Andrew Ng on Coursera
local nginx reverse proxy for macos
Markov chain implementation in C++ using Eigen utilities
Basic implementation represented at Code Camp Macedonia. MCL is unsupervised graph clustering algorithm based on simulation of stochastic flow in graphs.
Markov network or undirected graphical model is a set of random variables having a Markov property described by an undirected graph. In other words, a random field is said to be a Markov random field if it satisfies Markov properties. A Markov network or MRF is similar to a Bayesian network in its representation of dependencies; the differences being that Bayesian networks are directed and acyclic, whereas Markov networks are undirected and may be cyclic. Thus, a Markov network can represent certain dependencies that a Bayesian network cannot (such as cyclic dependencies); on the other hand, it can't represent certain dependencies that a Bayesian network can (such as induced dependencies). The underlying graph of a Markov random field may be finite or infinite.
A simple script to generate working product keys for Mathematica 11.3 based upon your MathID and a product key for a trial period. The full description on KeyGens for Mathematica will soon be available at my website
Location-based, augmented reality mobile game used as an interactive tourist guide through the city of Niš. View it at https://apkpure.com/micross/com.twoschool4cool.test123
Implementation of some basic Machine Learning algorithms in F#. Usually implemented on famous public datasets (Iris, Titanic, MNIST) depending on the problem.
Demo notebooks on the Multivariable Polynomial Regression and the Linear Algebra behind.
Implementation for the Neural Logic Machines (NLM). Not an official Google product. View it at https://sites.google.com/view/neural-logic-machines
code for deep learning courses
Some of my class notes, exercises and University homework for the first class of Object Oriented Programming, both in C++ and Java.
Learn OpenCL step by step.
Highly cited and useful papers related to machine learning, deep learning, AI, game theory, reinforcement learning
My demo project for the third year course of Web programming. The main idea was to create an useful tool to manage workers and jobs inside of the company. Technologies used: PHP, MySQL, Bootstrap, JQuery, JQuery UI
A Permutation Invariant Graph Classifier
Pytorch implementation of Pinet