# On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations

Source: [On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations](<https://www.sota2.com/research/paper/68fa71e11e209131cea5389d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:14:27.865Z

Authors: Euna Jung, Jaekeol Choi, EungGu Yun, Wonjong Rhee

Published: 2024-01-17T16:40:56.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2401.09518>)

[PDF](<https://arxiv.org/pdf/2401.09518.pdf>)
