论文标题
在线神经元控制的高性能进化算法
High-performance Evolutionary Algorithms for Online Neuron Control
论文作者
论文摘要
最近，优化已成为神经科学家研究神经代码的新兴工具。在视觉系统中，神经元对具有分级和嘈杂响应的图像做出反应。引起最高反应的图像模式是神经元的编码含量的诊断。为了找到这些模式，我们使用了黑框优化器来搜索4096D图像空间，从而导致图像的演变，从而最大程度地提高神经元响应。尽管通常使用了遗传算法（GA），但没有进行任何系统研究来揭示最佳性能优化器或改进它们所需的基本原理。 在这里，我们在优化器的计算机基准中进行了大规模的激活最大化，发现协方差矩阵适应（CMA）在其实现的激活方面表现出色。我们将CMA与GA进行了比较，发现CMA在计算机中超过66％的GA激活和44％的体内激活。我们分析了进化轨迹的结构，发现成功的关键不是协方差矩阵适应，而是局部搜索信息范围的尺寸和有效的步长衰减。在这些原理和图像歧管的几何形状的指导下，我们开发了球形优化器，该优化器与CMA竞争良好，证明了已确定的原理的有效性。代码可在https://github.com/animax-com/actmax-optimizer-dev上找到
Recently, optimization has become an emerging tool for neuroscientists to study neural code. In the visual system, neurons respond to images with graded and noisy responses. Image patterns eliciting highest responses are diagnostic of the coding content of the neuron. To find these patterns, we have used black-box optimizers to search a 4096d image space, leading to the evolution of images that maximize neuronal responses. Although genetic algorithm (GA) has been commonly used, there haven't been any systematic investigations to reveal the best performing optimizer or the underlying principles necessary to improve them. Here, we conducted a large scale in silico benchmark of optimizers for activation maximization and found that Covariance Matrix Adaptation (CMA) excelled in its achieved activation. We compared CMA against GA and found that CMA surpassed the maximal activation of GA by 66% in silico and 44% in vivo. We analyzed the structure of Evolution trajectories and found that the key to success was not covariance matrix adaptation, but local search towards informative dimensions and an effective step size decay. Guided by these principles and the geometry of the image manifold, we developed SphereCMA optimizer which competed well against CMA, proving the validity of the identified principles. Code available at https://github.com/Animadversio/ActMax-Optimizer-Dev
