Convolutional neural networks (CNN) are generally designed with a heuristic initialization of network architecture and trained for a certain task. This often leads to overparametrization after learning and induces redundancy in the information flow paths within the network. This robustness and reliability is at the increased cost of redundant computations. Several methods have been proposed which leverage metrics that quantify the redundancy in each layer. However, layer-wise evaluation in these methods disregards the long-range redundancy which exists across depth on account of the distributed nature of the features learned by the model. In this paper, we propose (i) a mechanism to empirically demonstrate the robustness in performance of a CNN on account of redundancy across its depth, (ii) a method to identify the systemic redundancy in response of a CNN across depth using the understanding of unit impulse response, we subsequently demonstrate use of these methods to interpret redundancy in few networks as example. These techniques provide better insights into the internal dynamics of a CNN
[1]
Geoffrey E. Hinton,et al.
Distilling a Neural Network Into a Soft Decision Tree
,
2017,
CEx@AI*IA.
[2]
Jianxin Wu,et al.
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
,
2017,
2017 IEEE International Conference on Computer Vision (ICCV).
[3]
Song Han,et al.
Learning both Weights and Connections for Efficient Neural Network
,
2015,
NIPS.
[4]
Yoshua Bengio,et al.
Gradient-based learning applied to document recognition
,
1998,
Proc. IEEE.
[5]
Guigang Zhang,et al.
Deep Learning
,
2016,
Int. J. Semantic Comput..
[6]
Simon Haykin,et al.
GradientBased Learning Applied to Document Recognition
,
2001
.
[7]
David B. Thomas,et al.
Redundancy-Reduced MobileNet Acceleration on Reconfigurable Logic for ImageNet Classification
,
2018,
ARC.