paper-with-me

Papers

Understanding Deep Neural Networks via Linear Separability of Hidden Layers

2023-07-26 · Chao Zhang, Xinyu Chen, Wensheng Li, Lixue Liu, Wei Wu, DaCheng Tao

In this paper, we measure the linear separability of hidden layer outputs to study the characteristics of deep neural networks. In particular, we first propose Minkowski difference based linear separability measures (MD-LSMs) to evaluate the linear separability degree of two points sets. Then, we demonstrate that there is a synchronicity between the linear separability degree of hidden layer outputs and the network training performance, i.e., if the updated weights can enhance the linear separability degree of hidden layer outputs, the updated network will achieve a better training performance, and vice versa. Moreover, we study the effect of activation function and network size (including width and depth) on the linear separability of hidden layers. Finally, we conduct the numerical experiments to validate our findings on some popular deep networks including multilayer perceptron (MLP), convolutional neural network (CNN), deep belief network (DBN), ResNet, VGGNet, AlexNet, vision transformer (ViT) and GoogLeNet.

📄 PDF Abstract BibTeX arXiv:2307.13962

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Inception Module An Inception Module is an image model block that aims to approximate an optimal local sparse structure in a CNN. Put simply, it allows for us to use multiple types of filter…
Kaiming Initialization 설명 없음
Residual Connection 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

Separability is not the best goal for machine learning

2018-07-08 · Wlodzislaw Duch

Neural networks use their hidden layers to transform input data into linearly separable data clusters, with a linear or a perceptron type output layer making the final projection on the line perpendicular to the discrimi…

BIG-bench Machine Learning

Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers

2023-06-09 · Andrea Apicella, Francesco Isgrò, Roberto Prevete

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to…

image-classificationImage Classification

Generalization of an Upper Bound on the Number of Nodes Needed to Achieve Linear Separability

2018-02-10 · Marjolein Troost, Katja Seeliger, Marcel van Gerven

An important issue in neural network research is how to choose the number of nodes and layers such as to solve a classification problem. We provide new intuitions based on earlier results by An et al. (2015) by deriving …

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning

2025-05-24 · Haolin Yang, Hakaze Cho, Yiqiao Zhong, Naoya Inoue

The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either special attention heads or task vectors at sp…

In-Context Learning

Large Language Models Encode Semantics and Alignment in Linearly Separable Representations

2025-07-13 · Baturay Saglam, Paul Kassianik, Blaine Nelson, Sajana Weerawardhena 외 arxiv

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related …