2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDMLSP-42.6
Paper Title LAYER-WISE INTERPRETATION OF DEEP NEURAL NETWORKS USING IDENTITY INITIALIZATION
Authors Shohei Kubota, Hideaki Hayashi, Kyushu University, Japan; Tomohiro Hayase, Fujitsu Laboratories, Japan; Seiichi Uchida, Kyushu University, Japan
SessionMLSP-42: Neural Network Pruning
LocationGather.Town
Session Time:Friday, 11 June, 11:30 - 12:15
Presentation Time:Friday, 11 June, 11:30 - 12:15
Presentation Poster
Topic Machine Learning for Signal Processing: [MLR-PRCL] Pattern recognition and classification
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization, where the input is randomly embedded into a different feature space in each layer. In this paper, we propose an interpretation method for a deep multilayer perceptron, which is the most general architecture of NNs, based on identity initialization (namely, initialization using identity matrices). The proposed method allows us to analyze the contribution of each neuron to classification and class likelihood in each hidden layer. As a property of the identity-initialized perceptron, the weight matrices remain near the identity matrices even after learning. This property enables us to treat the change of features from the input to each hidden layer as the contribution to classification. Furthermore, we can separate the output of each hidden layer into a contribution map that depicts the contribution to classification and class likelihood, by adding extra dimensions to each layer according to the number of classes, thereby allowing the calculation of the recognition accuracy in each layer and thus revealing the roles of independent layers, such as feature extraction and classification.