Figures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)

• UpdatedJun 10, 2022
• Python

Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)

• UpdatedAug 14, 2023
• R

A spreadsheet-like interactive evaluator for F#

• UpdatedOct 20, 2021
• F#

The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".

• UpdatedNov 19, 2021
• Python

Manipulation of geographical and statistical data in Java, with a focus on Eurostat data

• UpdatedMar 11, 2024
• Java

Code from the article: "The Role of Disentanglement in Generalisation" (ICLR, 2021).

• UpdatedMay 28, 2022
• Jupyter Notebook

Label smoothed Aggregation cross entropy loss for generalisation in sequence to sequence tasks.

• UpdatedDec 17, 2019
• Python

In the context of Deep Learning: What is the right way to conduct example weighting? How do you understand loss functions and so-called theorems on them?

• UpdatedMar 4, 2021
• Shell

Regularize polygons to rectilinear shape using constrained least squares in Java

• UpdatedAug 13, 2013
• Java

Investigation of how noise perturbations impact neural network calibration and generalisation

• UpdatedMar 26, 2024
• Shell

Code from the article: "Lost in Latent Space: Examining Failures of Disentangled Models at Combinatorial Generalisaton" (NeurIPS, 2022)

• UpdatedJan 4, 2023
• Python

LatentAugment, is a new data augmentation method for training any deep models. It navigates GAN's latent space to increase the diversity and quality of generated samples and enhance their effectiveness for DA purposes.

• UpdatedJul 24, 2023
• Python

This is a simple DAO for Java with some more features. I used it for my school project.

• UpdatedDec 16, 2023
• Java

Metrics to assess the generalisation ability of NILM algorithms

• UpdatedDec 16, 2019

Generalisation of electrical models of neurons with MCMC

• UpdatedFeb 26, 2025
• Python

Implementation for the ACL-Findings 2024 paper on memorisation localisation for NLP classification tasks.

• UpdatedAug 11, 2024
• Jupyter Notebook

Web-based dot map generalisation

• UpdatedJun 6, 2017
• JavaScript

Framework for benchmarking black-box adversarial attacks, modeled with ES.

• UpdatedMay 4, 2023
• Python

Supervised Learning - Regression Algorithm

• UpdatedDec 8, 2023
• Jupyter Notebook

Polynomials are mathematical objects which are expressions of variables and coefficients added to-gether. These polynomials can use operator overloading in a very intuitive manner since most of the operators that we can overload are mathematical operators, which can also be applied to polynomials.

• UpdatedOct 12, 2023
• C++