arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.11271cs.LG
收藏

IC神经元:构造神经网络的有效单元

IC Neuron: An Efficient Unit to Construct Neural Networks

Nanjing University(南京大学)

Junyi An, Fengshan Liu, Jian Zhao, Furao Shen

摘要:

神经网络作为一种流行的机器学习方法,可以用来解决许多复杂的任务。它们强大的泛化能力来自于基本神经元模型的表示能力。最流行的神经元是MP神经元,它使用线性变换和非线性激活函数来连续处理输入。受物理学中弹性碰撞模型的启发,我们提出了一种新的神经元模型,它可以表示更复杂的分布。我们称之为层间碰撞(IC)神经元。IC神经元将输入空间划分为用于表示不同线性变换的多个子空间。这种操作增强了非线性表示能力,并强调了一些有用的输入功能,为给定的任务。我们通过将IC神经元集成到全连接(FC),卷积和递归结构中来构建IC网络。在广泛的实验中,IC网络的性能优于传统网络。我们相信IC神经元可以成为构建网络结构的基本单元。

英文摘要:

As a popular machine learning method, neural networks can be used to solve many complex tasks. Their strong generalization ability comes from the representation ability of the basic neuron model. The most popular neuron is the MP neuron, which uses a linear transformation and a non-linear activation function to process the input successively. Inspired by the elastic collision model in physics, we propose a new neuron model that can represent more complex distributions. We term it Inter-layer collision (IC) neuron. The IC neuron divides the input space into multiple subspaces used to represent different linear transformations. This operation enhanced non-linear representation ability and emphasizes some useful input features for the given task. We build the IC networks by integrating the IC neurons into the fully-connected (FC), convolutional, and recurrent structures. The IC networks outperform the traditional networks in a wide range of experiments. We believe that the IC neuron can be a basic unit to build network structures.

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。

↑