Comparison of new activation functions in neural network for forecasting financial time series
Comparison of new activation functions in neural network for forecasting financial time series
复制标题
DOI：
10.1007/s00521-010-0407-3
复制
发表时间：
2011-04
影响因子：
6
通讯作者：
G. Gomes;Teresa B Ludermir;Leyla M. M. R. Lima-Leyla-M.-M.-R.-Lima-2066018903
中科院分区：
文献类型：
--
作者：
G. Gomes;Teresa B Ludermir;Leyla M. M. R. Lima-Leyla-M.-M.-R.-Lima-2066018903
在人工神经网络 (ANN) 中，实际中最常用的激活函数是逻辑 sigmoid 函数和双曲正切函数。据说，人工神经网络中使用的激活函数在学习算法的收敛中发挥着重要作用。在本文中，我们评估了不同激活函数的使用，并建议使用三个新的简单函数：互补的对数对数、概率和对数对数作为激活函数，以提高神经网络的性能。金融时间序列用于评估使用这些新激活函数的 ANN 模型的性能，并将其性能与文献中现有的一些激活函数进行比较。该评估通过两种学习算法进行：使用 Fletcher–Reeves 更新的共轭梯度反向传播和 Levenberg–Marquardt。
In artificial neural networks (ANNs), the activation function most used in practice are the logistic sigmoid function and the hyperbolic tangent function. The activation functions used in ANNs have been said to play an important role in the convergence of the learning algorithms. In this paper, we evaluate the use of different activation functions and suggest the use of three new simple functions, complementary log-log, probit and log-log, as activation functions in order to improve the performance of neural networks. Financial time series were used to evaluate the performance of ANNs models using these new activation functions and to compare their performance with some activation functions existing in the literature. This evaluation is performed through two learning algorithms: conjugate gradient backpropagation with Fletcher–Reeves updates and Levenberg–Marquardt.