paper-with-me

Papers

Computing Linear Regions in Neural Networks with Skip Connections

2025-09-18 · Johnny Joyce, Jan Verschelde arxiv

Neural networks are important tools in machine learning. Representing piecewise linear activation functions with tropical arithmetic enables the application of tropical geometry. Algorithms are presented to compute regions where the neural networks are linear maps. Through computational experiments, we provide insights on the difficulty to train neural networks, in particular on the problems of overfitting and on the benefits of skip connections.

📄 PDF Abstract BibTeX arXiv:2509.15441

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A General Computational Framework to Measure the Expressiveness of Complex Networks using a Tight Upper Bound of Linear Regions

2021-01-01 · Yutong Xie, Gaoxiang Chen, Quanzheng Li

The expressiveness of deep neural network (DNN) is a perspective to understand the surprising performance of DNN. The number of linear regions, i.e. pieces that a piece-wise-linear function represented by a DNN, is gener…

Efficient Skip Connections Realization for Secure Inference on Encrypted Data

2023-06-11 · Nir Drucker, Itamar Zimerman

Homomorphic Encryption (HE) is a cryptographic tool that allows performing computation under encryption, which is used by many privacy-preserving machine learning solutions, for example, to perform secure classification.…

Privacy Preserving

A General Computational Framework to Measure the Expressiveness of Complex Networks Using a Tighter Upper Bound of Linear Regions

2020-12-08 · Yutong Xie, Gaoxiang Chen, Quanzheng Li

The expressiveness of deep neural network (DNN) is a perspective to understandthe surprising performance of DNN. The number of linear regions, i.e. pieces thata piece-wise-linear function represented by a DNN, is general…

Select, Attend, and Transfer: Light, Learnable Skip Connections

2018-04-14 · Saeid Asgari Taghanaki, Aicha Bentaieb, Anmol Sharma, S. Kevin Zhou 외

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients. They equip en…

DecoderSegmentation

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth

2021-05-10 · Keyulu Xu, Mozhi Zhang, Stefanie Jegelka, Kenji Kawaguchi

Graph Neural Networks (GNNs) have been studied through the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the first step towards analyzing GNN traini…