Alejandro Mosquera's Projects
Solution for the AI-themed CTF held as part of DEFCON 30 using the Kaggle platform
My solution for Kagge Allen AI Challenge ( 3rd place )
A JavaScript procedural content generation tool
Python code for tree ensemble interpretation
A deodex script for reverse-engineering Android apps.
Code to share different ensemble techniques with focus on meta-stacking , using data from Amazon.com - Employee Access Challenge kaggle competition
Extremely simple one-shot learning in Python
Farbrausch demo tools 2001-2011
WebGL interactive fractal renderer
Feature-Time Instability Metric
Online live editor for fragment shaders.
Sample iPython notebook with soccer predictions
k-Met is a phonetic clustering algorithm for grouping words by their approximate pronunciation. It uses fuzzy matching techniques and the double metaphone indexing algorithm.
Kaggle 'Microsoft Malware Classification Challenge' 3rd place solution
1st Place Solution for Search Results Relevance Competition on Kaggle (https://www.kaggle.com/c/crowdflower-search-relevance)
code for kaggle competition Microsoft malware classification
A solution for Microsoft Malware Classification Challenge (BIG 2015)
A competition report for the 3rd edition of the Machine Learning Security Evasion Competition (MLSEC-2021)
NaiveSumm is a naive summarization approach based on Luhn1958 work "The Automatic Creation of Literature Abstracts" It uses the frequencies of words in the document in order to calculate and extract the sentences that include the most frequent words.
Normalized Compression Distance and Chess Games
Solution for the Trojan Detection Challenge (TDC2022 - https://trojandetection.ai) as part of NeurIPS 2022
Santa's Stolen Sleigh competition
Solution using adversarial training for the explainable detection of sexism in social networks (EDOS) task as part of SEMEVAL 2023
Python module for Simulated Annealing optimization
Metaphone is a phonetic algorithm, an algorithm published in 1990 for indexing words by their English pronunciation. It fundamentally improves on the Soundex algorithm by using information about variations and inconsistencies in English spelling and pronunciation to produce a more accurate encoding, which does a better job of matching words and names which sound similar. As with Soundex, similar sounding words should share the same keys.
Procedural texture editor in your browser