Dec 2, 2022
Speaker · 0 followers
Speaker · 0 followers
Speaker · 0 followers
Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with measurable aspects of interpretability and demonstrate it on fine-grained image classification. We argue that a human can only understand the decision of a machine learning model, if the input features are interpretable and only very few of them are used for a single decision. For that matter, the final layer has to be sparse and – to make interpreting the features feasible – low dimensional. We call a model with a Sparse Low-Dimensional Decision “SLDD-Model”. We show that a SLDD-Model is easier to interpret locally and globally than a dense high-dimensional decision layer while being able to maintain competitive accuracy. Additionally, we propose a loss function that improves a model’s feature diversity and accuracy. Our interpretable SLDD-Model only uses 5 out of just 50 features per class, while maintaining 97Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with measurable aspects of interpretability and demonstrate it on fine-grained image classification. We argue that a human can only understand the decision of a machine learning model, if the input features are interpretable and only very few of them are used for a si…
Account · 952 followers
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Lue Tao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Weirui Ye, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Haojie Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Hengyuan Hu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%