Archives
- Mon 31 October 2022
- Score Matching, Toy Datasets, and JAX
- Thu 25 February 2021
- Speed and power: fine-tuning distilled transformers models
- Fri 29 January 2021
- Multi-label classification with BERT
- Sat 29 February 2020
- Understanding the SHAP interpretation method: Kernel SHAP
- Fri 27 December 2019
- Understanding the SHAP interpretation method: Shapley values
- Sun 19 August 2018
- Few-shot learning in NLP: many-classes classification from few examples
- Tue 12 September 2017
- LIME of words: interpreting Recurrent Neural Networks predictions
- Mon 07 August 2017
- LIME of words: how to interpret your machine learning model predictions