Gabrijel Boduljak's Projects
Android Toolkit is an app for an Android device managment and modification. It has built in ADB Tools, Fastboot Tools and custom recovery flasher and much more. There is also support for remote ADB control
Android Toolkit is an app for an Android device managment and modification. It has built in ADB Tools, Fastboot Tools and custom recovery flasher and much more. There is also support for remote ADB control. Version V2 is being written in MVVM for perfomance, architecture and code improvement .
The thesis is "On universality of fully-connected neural networks". This thesis aims to present key results in the approximation theory of artificial neural networks assuming only undergraduate mathematics. This research field studies necessary and sufficient conditions under which neural networks can approximate certain functions.
A console based calculator written in Haskell.
📚 Solutions to Introduction to Algorithms Third Edition
This is a repository of pseudocode implementations discussed in the main text of a classic - 📖Introduction to Algorithms, known as CLRS. All implementations are written in C. The repository is a result of self study of algorithms discussed in CLRS.
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
Stanford CS1/CS143 Compilers Course Project - Cool compiler
COOL compiler implementation for Stanford's CS143 open course
Cross Tasky is a simple cross platform task managment app. Written in C++ and Qt framework. Built for purposes of learning Qt.
A PyTorch implementation of CyCADA
A quick and dirty implementation of Discrete Fourier transform (DFT) in Haskell. Tested on Polynomial Multiplication.
Learning diverse image-to-image translation from unpaired data
Implementations of functional pearls (https://wiki.haskell.org/Research_papers/Functional_pearls) I read.
Implementation of "Generate To Adapt: Aligning Domains using Generative Adversarial Networks"
An implementation of Graph Attention Networks (GAT) paper accompanied with the analysis of attention scores.
This study aims to show that group equivariant CNNs outperform spatial transformers, on tasks which demand rotation invariance, by providing theoretical background and experimental performance comparison with detailed analysis.
Lightweight attentional GAN for unpaired image-to-image-translation.
A repository of machine learning projects made for Kaggle competition and practicing machine learning models.
mcc is a toy compiler compiling a (relatively) large subset of C language to LLVM IR.
Learning multi-domain multi-modality I2I translation
MLX: An array framework for Apple silicon
Efficient framework-agnostic data loading
Examples in the MLX framework
A simple feed forward neural network implementation for predicting handwritten digits.
MNIST done with paper, pencil and Numpy
Multimodal Unsupervised Image-to-Image Translation
Official PyTorch implementation of NICE-GAN: Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
pixel da