paper-with-me

홈 › Papers

An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network

2021-04-05 · Anh Nguyen, Khoa Pham, Dat Ngo, Thanh Ngo, Lam Pham

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activation functions. Meanwhile, the second model, likely VGGish-based architecture, is applied for Acoustic Scene Classification (ASC) Task 1A in DCASE 2018 challenge, thus evaluate whether these activation functions work well in different datasets as well as different network architectures.

📄 PDF Abstract BibTeX arXiv:2104.02523

Code (0)

등록된 구현이 없습니다.

Tasks

Acoustic Scene ClassificationClassificationGeneral ClassificationScene Classification

Similar Papers 제목 키워드 기반

Fractal and Chaotic Activation Functions in Echo State Networks: Preprocessing Topology Governs the Echo State Property

2025-12-16 · Rae Chipera, Jenny Du, Irene Tsapara arxiv

Contemporary reservoir computing relies heavily on globally Lipschitz, well-behaved activation functions, limiting applications in defense, disaster response, and pharmaceutical modeling where robust operation under extr…

ErfReLU: Adaptive Activation Function for Deep Neural Network

2023-06-02 · Ashish Rajanand, Pradeep Singh

Recent research has found that the activation function (AF) selected for adding non-linearity into the output can have a big impact on how effectively deep learning networks perform. Developing activation functions that …

Fast generalization error bound of deep learning without scale invariance of activation functions

2019-07-25 · Yoshikazu Terada, Ryoma Hirose

In theoretical analysis of deep learning, discovering which features of deep learning lead to good performance is an important task. In this paper, using the framework for analyzing the generalization error developed in …

Deep Learning

SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks

2025-10-25 · Amin Omidvar arxiv

The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a novel two-phase training…

Computational Efficiency

MorphoActivation: Generalizing ReLU activation function by mathematical morphology

2022-07-13 · Santiago Velasco-Forero, Jesús Angulo

This paper analyses both nonlinear activation functions and spatial max-pooling for Deep Convolutional Neural Networks (DCNNs) by means of the algebraic basis of mathematical morphology. Additionally, a general family of…