凸高效编码
Convex Efficient Coding
AI总结:
本文提出了一种可 tractable 但灵活的规范性表征理论,通过优化表征相似性证明了一类凸优化问题,包括线性和非线性神经网络及半非负矩阵分解等,为神经编码提供了新的理论框架。
摘要:
为什么神经元以这种方式编码信息?规范性答案将神经活动建模为一个优化问题的解;例如,著名的高效编码假说将神经活动建模为在效率约束下信息的最优编码。成功的规范性理论在复杂性上差异很大,从简单的线性模型(Atick & Redlich '90)到复杂的深度神经网络(Lindsay '21)。复杂模型在灵活性上有所增加,但在可处理性 和可理解性上往往有所损失。在这里,我们折中处理,构建了一组可 tractable 但灵活的规范性表征理论。而不是直接优化神经活动,遵循 Sengupta 等人 '18 的方法,我们优化表征相似性,这是一种由每对神经响应的点积形成的矩阵。使用这种方法,我们证明了一大类有趣的优化问题是凸的。这一类包括对应于线性和某些非线性神经网络的优化问题,以及文献中以前未被识别为凸的优化问题,如修改版的半非负矩阵分解或非负稀疏编码。我们以三种方式应用这些发现。首先,我们为一种半非负矩阵分解形式提供了第一个必要且充分的可识别性结果。其次,我们表明如果神经调制是“足够不同”,那么它们会唯一地与最优的表征相似性相关联,部分证明了在神经科学中使用单个神经元调制分析的合理性。最后,我们利用某些问题的可 tractable 非线性特性来解释为什么密集视网膜代码,而不是稀疏皮层代码,最优地将单个变量的编码分成 ON 和 OFF 通道。总之,我们识别了一类凸问题,并利用它们推导出神经编码结果。
英文摘要:
Why do neurons encode information the way they do? Normative answers to this question model neural activity as the solution to an optimisation problem; for example, the celebrated efficient coding hypothesis frames neural activity as the optimal encoding of information under efficiency constraints. Successful normative theories have varied dramatically in complexity, from simple linear models (Atick & Redlich '90), to complex deep neural networks (Lindsay '21). What complex models gain in flexibility, they lose in tractability and often understandability. Here, we split the difference by constructing a set of tractable but flexible normative representational theories. Instead of optimising the neural activities directly, following Sengupta et al. '18, we optimise the representational similarity, a matrix formed from the dot products of each pair of neural responses. Using this, we show that a large family of interesting optimisation problems are convex. This family includes problems corresponding to linear and some non-linear neural networks, and problems from the literature not previously recognised as convex, such as modified versions of semi-nonnegative matrix factorisation or nonnegative sparse coding. We put these findings to work in three ways. First, we provide the first necessary and sufficient identifiability result for a form of semi-nonnegative matrix factorisation. Second, we show that if neural tunings are `different enough' then they are uniquely linked to the optimal representational similarity, partially justifying the use of single neuron tuning analysis in neuroscience. Finally, we use the tractable nonlinearity of some of our problems to explain why dense retinal codes, but not sparse cortical codes, optimally split the coding of a single variable into ON & OFF channels. In sum, we identify a space of convex problems, and use them to derive neural coding results.
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。