arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1402.4914cs.AIcs.ARstat.CO
收藏

用有意随机的数字部件构建快速贝叶斯计算机器

Building fast Bayesian computing machines out of intentionally stochastic, digital parts

MIT(麻省理工学院)

Vikash Mansinghka, Eric Jonas

摘要:

大脑使用比逻辑门更慢、更不可靠的神经元,比现代计算机更快、更可靠地解释模糊的感官信息。但是,贝叶斯推理是感知和认知的许多计算模型的基础,即使考虑到现代晶体管的速度和能量预算,它在计算上也具有挑战性。缩小这一差距所需的计算原理和结构是未知的。在这里,我们将展示如何使用有意随机的数字部件来构建快速的贝叶斯计算机器,从而将这种效率差距缩小多个数量级。我们发现,通过连接随机数字组件根据简单的数学规则,可以建立大规模并行,低精度的电路,解决贝叶斯推理问题,并与皮质神经元的泊松放电统计兼容。我们评估电路的深度和运动感知、感知学习和因果推理,每个电路都能实时的对10,000多个潜在变量进行推理-比商品微处理器的速度快1,000倍。这些结果表明,在智能计算的工程和逆向工程的随机性的一个新的角色。

英文摘要:

The brain interprets ambiguous sensory information faster and more reliably than modern computers, using neurons that are slower and less reliable than logic gates. But Bayesian inference, which underpins many computational models of perception and cognition, appears computationally challenging even given modern transistor speeds and energy budgets. The computational principles and structures needed to narrow this gap are unknown. Here we show how to build fast Bayesian computing machines using intentionally stochastic, digital parts, narrowing this efficiency gap by multiple orders of magnitude. We find that by connecting stochastic digital components according to simple mathematical rules, one can build massively parallel, low precision circuits that solve Bayesian inference problems and are compatible with the Poisson firing statistics of cortical neurons. We evaluate circuits for depth and motion perception, perceptual learning and causal reasoning, each performing inference over 10,000+ latent variables in real time - a 1,000x speed advantage over commodity microprocessors. These results suggest a new role for randomness in the engineering and reverse-engineering of intelligent computation.

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。

↑