paper-with-me

홈 › Papers

Singular Values for ReLU Layers

2018-12-06 · Sören Dittmer, Emily J. King, Peter Maass

Despite their prevalence in neural networks we still lack a thorough theoretical characterization of ReLU layers. This paper aims to further our understanding of ReLU layers by studying how the activation function ReLU interacts with the linear component of the layer and what role this interaction plays in the success of the neural network in achieving its intended task. To this end, we introduce two new tools: ReLU singular values of operators and the Gaussian mean width of operators. By presenting on the one hand theoretical justifications, results, and interpretations of these two concepts and on the other hand numerical experiments and results of the ReLU singular values and the Gaussian mean width being applied to trained neural networks, we hope to give a comprehensive, singular-value-centric view of ReLU layers. We find that ReLU singular values and the Gaussian mean width do not only enable theoretical insights, but also provide one with metrics which seem promising for practical applications. In particular, these measures can be used to distinguish correctly and incorrectly classified data as it traverses the network. We conclude by introducing two tools based on our findings: double-layers and harmonic pruning.

📄 PDF Abstract BibTeX arXiv:1812.02566

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Hankel Singular Value Regularization for Highly Compressible State Space Models

2025-10-27 · Paul Schwerdtner, Jules Berman, Benjamin Peherstorfer arxiv

Deep neural networks using state space models as layers are well suited for long-range sequence tasks but can be challenging to compress after training. We use that regularizing the sum of Hankel singular values of state…

Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning

2018-12-15 · Hock Hung Chieng, Noorhaniza Wahid, Pauline Ong, Sai Raj Kishore Perla

Activation functions are essential for deep learning methods to learn and perform complex tasks such as image classification. Rectified Linear Unit (ReLU) has been widely used and become the default activation function a…

General Classificationimage-classificationImage Classification

Bayesian Free Energy of Deep ReLU Neural Network in Overparametrized Cases

2023-03-28 · Shuya Nagayasu, Sumio Watanabe

In many research fields in artificial intelligence, it has been shown that deep neural networks are useful to estimate unknown functions on high dimensional input spaces. However, their generalization performance is not …

Learning Theory

Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice

2017-11-13 · NeurIPS 2017 12 · Jeffrey Pennington, Samuel S. Schoenholz, Surya Ganguli

It is well known that the initialization of weights in deep neural networks can have a dramatic impact on learning speed. For example, ensuring the mean squared singular value of a network's input-output Jacobian is $O(1…

Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations

2025-10-28 · Alexandru Crăciun, Debarghya Ghoshdastidar arxiv

The theory of training deep networks has become a central question of modern machine learning and has inspired many practical advancements. In particular, the gradient descent (GD) optimization algorithm has been extensi…