arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.07114cs.LGstat.ML
收藏

从核心对象识别的角度深入研究$β$ - VAE中解纠缠表示的无监督学习

A Deeper Look at the Unsupervised Learning of Disentangled Representations in $β$-VAE from the Perspective of Core Object Recognition

Harvard University(哈佛大学)

Harshvardhan Sikka

摘要:

识别物体的能力,尽管存在外观上的差异,被称为核心物体识别,形成了人类感知的关键部分。虽然可以理解,大脑通过视觉流的前馈、分层计算来完成核心对象识别,但允许下游形成不变表示的底层算法仍然没有得到很好的理解。(DiCarlo等人,已经建立了各种计算感知模型来尝试和解决人工感知设置中的对象识别任务。人工神经网络是由加权边和顶点处的数学运算组成的计算图,其灵感大致来自大脑中的神经网络,并且已被证明在各种视觉感知任务中是有效的,包括对象表征和识别。(Pinto等人,2008)(DiCarlo等人,对于许多数据分析任务,学习表示,其中每个维度在统计上是独立的,因此与其他维度分离是有用的。如果数据的潜在生成因素在统计上也是独立的,则潜变量的贝叶斯推断可以形成分离的表示。本论文是一个研究计画,探讨变分自编码器(VAE)的推广,$β$ -VAE,其目的是使用变分推理来学习解纠缠表示。$β$ -VAE包含超参数$β$,并强制其瓶颈神经元的条件独立性,这通常与潜在变量的统计独立性不兼容。本文探讨这种架构,并提供了分析和数值参数,目的是证明这种不兼容性导致非单调推理性能在$β$ -VAE有限的最佳$β$。

英文摘要:

The ability to recognize objects despite there being differences in appearance, known as Core Object Recognition, forms a critical part of human perception. While it is understood that the brain accomplishes Core Object Recognition through feedforward, hierarchical computations through the visual stream, the underlying algorithms that allow for invariant representations to form downstream is still not well understood. (DiCarlo et al., 2012) Various computational perceptual models have been built to attempt and tackle the object identification task in an artificial perceptual setting. Artificial Neural Networks, computational graphs consisting of weighted edges and mathematical operations at vertices, are loosely inspired by neural networks in the brain and have proven effective at various visual perceptual tasks, including object characterization and identification. (Pinto et al., 2008) (DiCarlo et al., 2012) For many data analysis tasks, learning representations where each dimension is statistically independent and thus disentangled from the others is useful. If the underlying generative factors of the data are also statistically independent, Bayesian inference of latent variables can form disentangled representations. This thesis constitutes a research project exploring a generalization of the Variational Autoencoder (VAE), $β$-VAE, that aims to learn disentangled representations using variational inference. $β$-VAE incorporates the hyperparameter $β$, and enforces conditional independence of its bottleneck neurons, which is in general not compatible with the statistical independence of latent variables. This text examines this architecture, and provides analytical and numerical arguments, with the goal of demonstrating that this incompatibility leads to a non-monotonic inference performance in $β$-VAE with a finite optimal $β$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑