All software
FedvsCent
Code supporting chapter 3 of the PhD thesis: "A comprehensive experimental comparison between federated and centralized learning Open Access"
- benchmark
- complex models
- Distributed data
- + 3
eEecology Classification
Automatic classification of accelerometer data using a supervised learning approach.
- Machine learning
- (Batchfile)
- (CSS)
- (HTML)
- + 3
mexca
Capture emotion expressions from video, audio, and text with a single pipeline.
- Audio processing
- Image processing
- Machine learning
- + 1
- (Dockerfile)
- (Python)
- (Shell)
sv-channels
Genome-wide detection of structural variants using deep learning
- Machine learning
- ("Jupyter Notebook")
- (Python)
- (R)
- + 1
Hercules
Retrieve recent tweets from certain users and classify them with machine learning
- Machine learning
- Text analysis & natural language processing
- ("Jupyter Notebook")
- (Python)
- (Shell)
BrazilClim: script to gauge-calibrate the surfaces
BrazilClim: script to gauge-calibrate the surfaces
- Bioclimatic variables
- Brazil
- land surface temperatures
- + 4
Combining-Deeb-Learning-with-Uncertinity
Code and results underlying the publication: Combining Deep Neural Networks and Gaussian Processes for Asphalt Rheological Insights
- Asphalt binder
- Asphalt mastic
- Gaussian process
- + 3
- ("Jupyter Notebook")
- (Markdown)
- (Other)
- + 1
AstronomicAL
An interactive dashboard for visualisation, integration and classification of data using Active Learning.
- Active Learning
- Classification
- Data Analysis
- + 11
- (Python)
- (TeX)
chimp-classifier
The Python package `junglesounds` is a machine learning pipeline for classifying bioacoustic data using machine learning. The pipeline is reusable for other settings and species or vocalization types as long as a certain amount of labeled data has been collected.
- audio
- Audio processing
- bioacoustics
- + 2
- ("Jupyter Notebook")
- (Python)
- (Shell)
Code supporting the paper: High-speed predictions of post-burn contraction using a neural network trained on 2D-finite element simulations
Code supporting the paper: High-speed predictions of post-burn contraction using a neural network trained on 2D-finite element simulations
- Feedforward neural network
- Machine learning
- Monte Carlo simulations
- + 2
MOTrainer
Measurement Operator Trainer for data assimilation purposes.
- Data assimilation
- High performance computing
- Machine learning
- + 2
- ("Jupyter Notebook")
- (Python)
- (Shell)
- + 1
NEWSGAC platform
Software for running the online platform of the NEWSGAC project for running explainable machine learning models on textual data
- Explainable AI
- Machine learning
- Text analysis & natural language processing
- (CSS)
- (Dockerfile)
- (HTML)
- + 4