Filip Cornell's Projects
Advent of code 2021
A library for exploring persistent homology
Contains code for my master's dissertation on applied topology.
An interpreter of brainfuck code instructions. Implemented with List structures in C++.
Repository for the code for the paper "Challenging the Assumption of Structure-based embeddings in Few- and Zero-shot Knowledge Graph Completion" published at LREC 2022.
The latent bag of words model for paraphrase generation
A tutorial on Docker
A template for a typical DS project
An efficient Python implementation of the Apriori algorithm.
Repository for the code for the paper Symbolic Hyperdimensional Vectors with Sparse Graph Convolutional Neural Networks, published at IJCNN 2022.
This is the repo for the Giotto-tda use-cases challenge 2020.
Project from 2018, performing hatespeech classification with a Convulotional Neural Network model. Comparing with logistic regression and XGBoost.
Implemented Machine Learning Algorithms in Hyperbolic Geometry (MDS, K-Means, Support vector machines, etc.)
Inteligencia Artificial - Project work in Artificial intelligence course. Implemented forward-checking on Green-Vehicle Routing problem. Was not an efficient algorithm.
A lightweight Python library that can be used to get live data from IG Markets REST and STREAM API with a LIVE or DEMO account
Convert an img to a character image!
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Kaggle playaround
LibKGE - A knowledge graph embedding library for reproducible research
Multi-Hop Logical Reasoning in Knowledge Graphs
Fast computation of the smallest enclosing ball of a point set, in low or moderately high dimensions.
Fast and memory-efficient clustering + coreset construction, including fast distance kernels for Bregman and f-divergences.
Side project worked on when there is time. Intention is to implement algorithms from scratch and visualize, preferrably with 2D-data.
Topological Data Analysis in Python: Simplicial Complex
A comparison of different algorithms for the k-armed bandit problem made in 2018.
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
Pre-trained models and code and data to train and use models from "Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations"
Sentence paraphrase generation at the sentence level