Difference between revisions of "Explainable Decision Forest"
From ISLAB/CAISR
| Line 1: | Line 1: | ||
{{StudentProjectTemplate | {{StudentProjectTemplate | ||
| − | |Summary=Designing | + | |Summary=Designing a deep model that uses decision trees instead of artificial neurons |
| − | |Keywords=decision forest, explainable AI | + | |Keywords=deep decision forest, explainable AI |
| − | |TimeFrame=Autumn | + | |TimeFrame=Autumn 2024 |
| − | |Supervisor= | + | |Supervisor=Sławomir Nowaczyk, |
|Status=Open | |Status=Open | ||
}} | }} | ||
| − | + | The success of Deep Learning is largely attributed to the ability to create/extract "hierarchical features" from the data. This is successful using artificial neurons or perceptrons, and the backpropagation algorithm. | |
| − | + | The price is, however, the very large size of the model, which translates into computational costs and a "black-box" nature, or lack of explainability. | |
| + | |||
| + | This project aims to explore ways to train a deep model using a chain of decision trees, like layers in a neural network. It promises to significantly reduce model complexity and increase interpretability. | ||
Revision as of 21:16, 24 August 2024
| Title | Explainable Decision Forest |
|---|---|
| Summary | Designing a deep model that uses decision trees instead of artificial neurons |
| Keywords | deep decision forest, explainable AI |
| TimeFrame | Autumn 2024 |
| References | |
| Prerequisites | |
| Author | |
| Supervisor | Sławomir Nowaczyk |
| Level | |
| Status | Open |
The success of Deep Learning is largely attributed to the ability to create/extract "hierarchical features" from the data. This is successful using artificial neurons or perceptrons, and the backpropagation algorithm.
The price is, however, the very large size of the model, which translates into computational costs and a "black-box" nature, or lack of explainability.
This project aims to explore ways to train a deep model using a chain of decision trees, like layers in a neural network. It promises to significantly reduce model complexity and increase interpretability.
