Roberto Rey-de-Castro's repositories
adversarial-perturbations-on-images-and-videos
Code and data from the paper "Targeted Nonlinear Adversarial Perturbations in Images and Videos".
presidential-elections-from-a-data-science-perspective
An exploration of historical data on US presidential elections
keyword-search
Find (possibly unknown) keywords associated to other (known) keywords.
churn-prediction-with-pyspark-and-keras
A distributed approach for data exploration, neural net training prediction and scoring. The modules are intended to handle large datasets by only operating in batches. The specific problem studied here is related to predicting the churn ratio (i.e., the amount of customers that leave a service) from a telecommunications company.
deep-explanation-using-ai-for-explaining-the-results-of-ai
A deep convolutional neural network is used to explain the results of another one (VGG19).
AWS-S3-Helper
Helper functions for navigating and getting data from an Amazon simple storage service (S3).
classification_using_transformers
Finetune transformer model trained on Wikipedia on a smaller corpus for classification (99% IMDB validation accuracy).
deep-learning-in-the-laser-lab
Analysis of ultrafast laser experiments using deep convolutional neural networks.
Running-experiments-from-Python-LabView-wrapper
A wrapper to setup, run, and retrieve the outputs from LabView vis from Python code.
sampling-of-biased-physical-signals
A method for sampling a balanced dataset from biased signals by leveraging statistical distributions derived from the data.