Adaptive Activation Thresholding: Dynamic Routing Type Behavior for Interpretability in Convolutional Neural Networks
There is a growing interest in strategies that can help us understand or interpret neural networks -- that is, not merely provide a prediction, but also offer additional context explaining why and how. While many current methods offer tools to perform this analysis for a given (trained) network post-hoc, recent results (especially on capsule networks) suggest that when classes map to a few high level "concepts" in the preceding layers of the network, the behavior of the network is easier to interpret or explain. Such training may be accomplished via dynamic/EM routing where the network "routes" for individual classes (or subsets of images) are dynamic and involve few nodes even if the full network may not be sparse. In this paper, we show how a simple modification of the SGD scheme can help provide dynamic/EM routing type behavior in convolutional neural networks. Through extensive experiments, we evaluate the effect of this idea for interpretability where we obtain promising results, while also showing that no compromise in attainable accuracy is involved. Further, we show that the minor modification is seemingly ad-hoc, the new algorithm can be analyzed by an approximate method which provably matches known rates for SGD.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sensitivity-Aware Thresholding and Token Routing for Activation Sparsification in Large Language Models
Efficient inference in Large Language Models (LLMs) requires deciding where computation can be reduced while preserving model quality. We study this problem through multilayer perceptron (MLP) activation sparsification a…
GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models
With the increase in model parameters and training data, the instruction following and generalization capabilities of Large VisionLanguage Models (LVLMs) have been significantly improved. Based on the Mixture of Experts …
Instruction FollowingLong cycles in linear thresholding systems
Linear thresholding systems have been used as a model of neural activation and more recently proposed as a model of gene regulation. Here we exhibit linear thresholding systems whose dynamics produce surprisingly long cy…
DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks
Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling neural networks while maintaining computational efficiency. However, standard MoE implementations rely on two rigid design assumption…
Computational EfficiencyImage ClassificationAttention routing between capsules
In this paper, we propose a new capsule network architecture called Attention Routing CapsuleNet (AR CapsNet). We replace the dynamic routing and squash activation function of the capsule network with dynamic routing (Ca…
Decoder