Algorithm selection using deep learning without feature extraction
Algorithm selection using deep learning without feature extraction
复制标题
使用深度学习进行算法选择，无需特征提取
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
E. Hart
中科院分区：
文献类型：
--
作者：
M. Alissa;Kevin Sim;E. Hart
我们提出了一种新的算法选择技术，该技术采用深度学习方法，特别是具有长短期记忆的递归神经网络（RNN-LSTM）。与算法选择中的大多数工作相反，该方法不需要从数据中提取任何特征，而是依赖于时间数据序列作为输入。一个大的案例研究领域的1-D装箱进行的情况下，可以解决的四个histologics之一。我们首先演化出大量新问题实例，每个实例都有一个明确的“最佳求解器”（根据所考虑的启发式方法）。RNN-LSTM直接使用描述每个实例的序列数据进行训练，以预测性能最佳的启发式算法。对具有从两种不同概率分布生成的项目大小的小型和大型问题实例进行的实验表明，与单个最佳求解器（SBS）（即在实例集上实现最佳性能的单个启发式算法）相比，实现了7%至11%的改进，并且比虚拟最佳求解器（VBS）低0%至2%，即完美映射。
We propose a novel technique for algorithm-selection which adopts a deep-learning approach, specifically a Recurrent-Neural Network with Long-Short-Term-Memory (RNN-LSTM). In contrast to the majority of work in algorithm-selection, the approach does not need any features to be extracted from the data but instead relies on the temporal data sequence as input. A large case-study in the domain of 1-d bin packing is undertaken in which instances can be solved by one of four heuristics. We first evolve a large set of new problem instances that each have a clear "best solver" in terms of the heuristics considered. An RNN-LSTM is trained directly using the sequence data describing each instance to predict the best-performing heuristic. Experiments conducted on small and large problem instances with item sizes generated from two different probability distributions are shown to achieve between 7% to 11% improvement over the single best solver (SBS) (i.e. the single heuristic that achieves the best performance over the instance set) and 0% to 2% lower than the virtual best solver (VBS), i.e the perfect mapping.
影响因子：
14.4
作者：
Hutter, Frank;Xu, Lin;Leyton-Brown, Kevin
通讯作者：
Leyton-Brown, Kevin