论文标题
贝叶斯的感知：朝向完全贝叶斯神经网络
Bayesian Perceptron: Towards fully Bayesian Neural Networks
论文作者
论文摘要
人工神经网络（NNS）已成为机器学习的事实上的标准。它们允许在大量应用中学习高度非线性的转换。但是，NN通常仅提供点估计，而无需系统地量化相应的不确定性。在本文中，提出了一种新的贝叶斯NNS的新方法，在贝叶斯推理框架内以封闭形式进行了训练和预测。权重和感知的预测被认为是高斯随机变量。用于预测感知龙的输出和学习权重的分析表达式提供了常用的激活函数，例如Sigmoid或Relu。这种方法不需要计算昂贵的梯度计算，并且可以进一步允许顺序学习。
Artificial neural networks (NNs) have become the de facto standard in machine learning. They allow learning highly nonlinear transformations in a plethora of applications. However, NNs usually only provide point estimates without systematically quantifying corresponding uncertainties. In this paper a novel approach towards fully Bayesian NNs is proposed, where training and predictions of a perceptron are performed within the Bayesian inference framework in closed-form. The weights and the predictions of the perceptron are considered Gaussian random variables. Analytical expressions for predicting the perceptron's output and for learning the weights are provided for commonly used activation functions like sigmoid or ReLU. This approach requires no computationally expensive gradient calculations and further allows sequential learning.
