CLAP-interpretable-predictions

KO | EN

gitlite — search

#javascript #python #hacktoberfest #typescript #llm #android #machine-learning #rust #deep-learning #java #awesome #kubernetes #mcp #open-source

CLAP-interpretable-predictions

(★ 15)

Official codebase for the paper "Provable concept learning for interpretable predictions using variational inference".

CLAP-interpretable-predictions Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# CLAP Interpretable Predictions 👏🏻
Official codebase for the paper <br />

[1] _Provable concept learning for interpretable predictions using variational inference_, <br /> 
Taeb A., Ruggeri N., Schnuck C., Yang F.  <br /> 
([Arxiv preprint](https://arxiv.org/abs/2204.00492))

![](https://raw.githubusercontent.com/nickruggeri/CLAP-interpretable-predictions/main/figures/CLAP_chestxray.png)

We present _CLAP_, an inherently interpretable prediction model. <br />
Its VAE-based architecture allows the discovery and disentanglement of relevant concepts, encoded in the latent space, 
which are utilized by a simple, concurrently trained classifier.   
The final architecture allows to exploit provably interpretable, predictive and minimal concepts to assist practitioners 
in making informed predictions.

### Code usage
To start training _CLAP_ on a dataset:

- download the desired dataset and place it in the `./data` directory. 
Alternatively, change the default data directory specified at `src.data.utils.DATA_DIR`
- run the terminal command. The datasets available are 
`MPI`, `Shapes3D`, `SmallNORB`, `ChestXRay`, `PlantVillage` [1].

For example, to train _CLAP_ on the `MPI` dataset, the terminal command is
```python
python main.py --dataset MPI
```
More options for training, e.g. latent space dimension and regularization parameters, are specified inside `main.py`.

CLAP-interpretable-predictions

CLAP-interpretable-predictions Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

CLAP-interpretable-predictions

CLAP-interpretable-predictions Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README