Lifelong Machine Learning Test
暂无分享,去创建一个
In this paper, we propose to measure the intelligence of an agent by measuring how fast its knowledge level increases after learning related tasks. In this paper, we propose a new Lifelong Machine Learning Test. An agent can pass the test if it can learn unrestricted number of tasks over time and its knowledge level can increase when new tasks are learned. In the proposed test, both an agent’s current performance and its performance growth rate are taking into account. We also give a new theoretical requirement and a novel empirical evaluation metric for the proposed lifelong machine learning test.
[1] Gábor Lugosi,et al. Introduction to Statistical Learning Theory , 2004, Advanced Lectures on Machine Learning.