On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations
Understanding the encoded representation of Deep Neural Networks (DNNs) has been a fundamental yet challenging objective. In this work, we focus on two possible directions for analyzing representations of DNNs by studying simple image classification tasks. Specifically, we consider \textit{On-Off pattern} and \textit{PathCount} for investigating how information is stored in deep representations. On-off pattern of a neuron is decided as on' or off' depending on whether the neuron's activation after ReLU is non-zero or zero. PathCount is the number of paths that transmit non-zero energy from the input to a neuron. We investigate how neurons in the network encodes information by replacing each layer's activation with On-Off pattern or PathCount and evaluating its effect on classification performance. We also examine correlation between representation and PathCount. Finally, we show a possible way to improve an existing DNN interpretation method, Class Activation Map (CAM), by directly utilizing On-Off or PathCount.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Simple Path Structural Encoding for Graph Transformers
Graph transformers extend global self-attention to graph-structured data, achieving notable success in graph learning. Recently, random walk structural encoding (RWSE) has been found to further enhance their predictive p…
Graph LearningInterpretable multi-timescale models for predicting fMRI responses to continuous natural speech
Natural language contains information at multiple timescales. To understand how the human brain represents this information, one approach is to build encoding models that predict fMRI responses to natural language using …
On the Suitability of Representations for Quality Diversity Optimization of Shapes
The representation, or encoding, utilized in evolutionary algorithms has a substantial effect on their performance. Examination of the suitability of widely used representations for quality diversity optimization (QD) in…
DiversityEvolutionary AlgorithmsEfficiency Analysis of ASP Encodings for Sequential Pattern Mining Tasks
This article presents the use of Answer Set Programming (ASP) to mine sequential patterns. ASP is a high-level declarative logic programming paradigm for high level encoding combinatorial and optimization problem solving…
Sequential Pattern MiningIncremental Data-Uploading for Full-Quantum Classification
The data representation in a machine-learning model strongly influences its performance. This becomes even more important for quantum machine learning models implemented on noisy intermediate scale quantum (NISQ) devices…
ClassificationQuantum Machine Learning