arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.03189cs.LGcs.NE
收藏

Forward-Forward 学习概念在多输出感知机中的应用

The Concept of Forward-Forward Learning Applied to a Multi Output Perceptron

Saab Dynamics(萨博动力公司)

K. Fredrik Karlsson

AI总结:

本文将 Forward-Forward 学习算法应用于单个多输出感知机进行分类,通过调整参数优化样本的“goodness”,实验表明该方法能有效处理非线性决策边界且性能媲美复杂网络,仅需单次矩阵乘法。

摘要:

将近期提出的用于全连接人工神经网络的 Forward-Forward 学习算法概念应用于单个多输出感知机进行分类。系统参数通过增加(减少)正确(错误)标记输入样本的“goodness”来训练。基础数值测试表明,训练后的感知机能有效处理具有非线性决策边界的数据集。此外,其整体性能可与带有隐藏层的更复杂神经网络相媲美。该方法的优势在于仅涉及单次矩阵乘法。

英文摘要:

The concept of a recently proposed Forward-Forward learning algorithm for fully connected artificial neural networks is applied to a single multi output perceptron for classification. The parameters of the system are trained with respect to increased (decreased) "goodness" for correctly (incorrectly) labelled input samples. Basic numerical tests demonstrate that the trained perceptron effectively deals with data sets that have non-linear decision boundaries. Moreover, the overall performance is comparable to more complex neural networks with hidden layers. The benefit of the approach presented here is that it only involves a single matrix multiplication.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑