VIP内容
论文链接：https://arxiv.org/pdf/2003.03384.pdf
GitHub 项目地址：https://github.com/google-research/google-research/tree/master/automl_zero#automl-zero
在这项研究中，谷歌提出了新方法 AutoML-Zero，该方法从空程序（empty program）开始，仅使用基本的数学运算作为构造块，使用进化方法来自动找出完整 ML 算法的代码。
在一些小的图像分类问题上，AutoML-Zero 方法重新发现了一些基本的 ML 技巧，如具备反向传播的双层神经网络和线性回归等，而这些是之前的研究人员经过数年时间才发现的。
这一结果表明，自动发现更新颖的 ML 算法以解决更棘手的问题，这一想法在未来是可行的。
接下来，我们来看 AutoML-Zero 方法的具体实现原理。
成为VIP会员查看完整内容
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
热门内容
最新内容
最新论文
Automated Machine Learning (AutoML) has emerged to deal with the selection and configuration of algorithms for a given learning task. With the progression of AutoML, several effective methods were introduced, especially for traditional classification and regression problems. Apart from the AutoML success, several issues remain open. One issue, in particular, is the lack of ability of AutoML methods to deal with different types of data. Based on this scenario, this paper approaches AutoML for multi-label classification (MLC) problems. In MLC, each example can be simultaneously associated to several class labels, unlike the standard classification task, where an example is associated to just one class label. In this work, we provide a general comparison of five automated multi-label classification methods -- two evolutionary methods, one Bayesian optimization method, one random search and one greedy search -- on 14 datasets and three designed search spaces. Overall, we observe that the most prominent method is the one based on a canonical grammar-based genetic programming (GGP) search method, namely Auto-MEKA$_{GGP}$. Auto-MEKA$_{GGP}$ presented the best average results in our comparison and was statistically better than all the other methods in different search spaces and evaluated measures, except when compared to the greedy search method.
