论文标题
用多层关系网络解决乌鸦的渐进式矩阵
Solving Raven's Progressive Matrices with Multi-Layer Relation Networks
论文作者
论文摘要
Raven的渐进式矩阵是最初旨在测试人类认知能力的基准。它最近已适应机器学习系统中的关系推理。为此，设置了所谓的程序生成的矩阵数据集，这是迄今为止最困难的关系推理基准之一。在这里，我们表明，深层神经网络能够解决该基准测试，通过将野生关系网络与多层关系网络相结合并引入幅度编码，这是一种较晚的融合方案，与先前最新的62.6％相比，准确性为98.0％。
Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.
