论文标题
决策集：二进制结构化神经网络
DecisioNet: A Binary-Tree Structured Neural Network
论文作者
论文摘要
深神经网络（DNN）和决策树（DTS）都是最新的分类器。 DNN由于其表示性学习能力而表现良好，而DTS在计算上是有效的，因为它们沿着一种取决于输入数据的途径（根到叶子）进行推理。在本文中，我们介绍了二元树结构化神经网络的决策者（DN）。我们提出了一种系统的方法，将现有DNN转换为DN，以创建原始模型的轻量级版本。 Decisionet竭尽所能 - 它使用神经模块来执行代表性学习，并利用其树结构仅执行一部分计算。我们评估了各种DN架构，以及它们在FashionMnist，CIFAR10和CIFAR100数据集上的相应基线模型。我们表明，DN变体具有相似的精度，同时大大降低了原始网络的计算成本。
Deep neural networks (DNNs) and decision trees (DTs) are both state-of-the-art classifiers. DNNs perform well due to their representational learning capabilities, while DTs are computationally efficient as they perform inference along one route (root-to-leaf) that is dependent on the input data. In this paper, we present DecisioNet (DN), a binary-tree structured neural network. We propose a systematic way to convert an existing DNN into a DN to create a lightweight version of the original model. DecisioNet takes the best of both worlds - it uses neural modules to perform representational learning and utilizes its tree structure to perform only a portion of the computations. We evaluate various DN architectures, along with their corresponding baseline models on the FashionMNIST, CIFAR10, and CIFAR100 datasets. We show that the DN variants achieve similar accuracy while significantly reducing the computational cost of the original network.
