Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are proven to be effective due to their ability to form increasingly complex abstractions. However, these abstractions are distributed over many neurons, making the re-use of a learned skill costly. Previous work either enforced formation of abstractions creating a designer bias, or used a large number of neural units without investigating how to obtain high-level features that may more effectively capture the source task. For avoiding designer bias and unsparing resource use, we propose to exploit neural response dynamics to form compact representations to use in skill transfer. For this, we consider two competing methods based on (1) maximum information compression principle and (2) the notion that abstract events tend to generate slowly changing signals, and apply them to the neural signals generated during task execution. To be concrete, in our simulation experiments, we either apply principal component analysis (PCA) or slow feature analysis (SFA) on the signals collected from the last hidden layer of a deep network while it performs a source task, and use these features for skill transfer in a new target task. We compare the generalization performance of these alternatives with the baselines of skill transfer with full layer output and no-transfer settings. Our results show that SFA units are the most successful for skill transfer. SFA as well as PCA, incur less resources compared to usual skill transfer, whereby many units formed show a localized response reflecting end-effector-obstacle-goal relations. Finally, SFA units with lowest eigenvalues resembles symbolic representations that highly correlate with high-level features such as joint angles which might be thought of precursors for fully symbolic systems.
翻译:抽象是情报的一个重要方面,它使代理商能够为有效决策建立强有力的代表。在过去十年中,深层次的网络由于能够形成日益复杂的抽象而证明是有效的。然而,这些抽象分布在许多神经元中,使得重新使用学到的技能成本很高。以前的工作要么是强制形成抽象,造成设计师偏差,要么是使用大量神经元单位,而没有调查如何获得可能更有效地捕捉源任务的高层次特征。为了避免设计师偏差和不分割资源使用,我们提议利用神经反应动力形成缩压式代表,用于技能转让。为此,我们考虑两种基于:(1) 最大信息压缩原则和(2) 抽象事件往往产生缓慢变化信号的概念,并将其应用到任务执行期间产生的神经信号上。具体地说,我们要么在从深层次网络最后隐藏层收集的信号上进行主要组成部分分析(PCA) 或缓慢的特征分析(SFA),在进行源任务时,我们利用这些特征来形成骨质化演示,在新的目标任务中进行技能转让。我们把这些最低层次的特性特征特征特征特征与S-AA级结构进行对比,从而显示我们高层次的技术转移的等级,从而显示S-AFAA级转移是完全的层次结构。