AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Deep Learning for Case-Based Reasoning Through Prototypes: A Neural Network That Explains Its Predictions

Oscar Li, Hao Liu, Chaofan Chen, Cynthia Rudin

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 581 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace the prototype layer with an equal-sized fully connected layer (ablation)Prototype network · MNIST testaccuracy: 99.22% -> 99.24%No clear effect
remove the decoder and prototype layer and use ReLU (ablation)Prototype network · MNIST testaccuracy: 99.22% -> 99.23%No clear effect
add both R1 and R2 prototype regularization terms (ablation)Prototype network · Carsdecoded prototype realismImproved
add R1 prototype-to-example regularization (ablation)Prototype network · Carsdecoded prototype realismImproved
add R2 example-to-prototype regularization (ablation)Prototype network · Carsprototype coverage and distinctnessImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy