.png){kind=icon}
Return
Improving Interpretability and Regularization in Deep Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2017.2774919.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep learning approaches yield state-of-the-art performance in a range of tasks, including automatic speech recognition. However, the highly distributed representation in a deep neural network (DNN) or other network variations is difficult to analyze, making further parameter interpretation and regularization challenging. This paper presents a regularization scheme acting on the activation function output to improve the network interpretability and regularization. The proposed approach, referred to as activation regularization, encourages activation function outputs to satisfy a target pattern. By defining appropriate target patterns, different learning concepts can be imposed on the network. This method can aid network interpretability and also has the potential to reduce overfitting. The scheme is evaluated on several continuous speech recognition tasks: the Wall Street Journal continuous speech recognition task, eight conversational telephone speech tasks from the IARPA Babel program and a U.S. English broadcast news task. On all the tasks, the activation regularization achieved consistent performance gains over the standard DNN baselines.
Keywords:
Activation regularisation
interpretability
visualisation
neural network
deep learning
Journal
I
IF:
5.1
Papers:
2.6K
Citations:
1.1W
Organization
Cited Papers
ShareSaveAnterior chamber‐associated immune deviation‐inducing cells activate T cells, and rescue them from antigen‐induced apoptosis.png)
Immunology
OAAI
ImmunologyIF0
OAAIShareSaveShareSaveShareSaveShareSaveShareSaveShareSaveSupporting Group Coherence in a Museum VisitProceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social ComputingOAAI
Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social ComputingIF0
OAAIShareSaveShareSave
View more