This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals,
a novel data indexing technique for approximate nearest neighbor (ANN) search.
SOAR extends upon previous approaches to ANN search, such as spill trees, that
utilize multiple redundant representations while partitioning the data to
reduce the probability of missing a nearest neighbor during search. Rather than
training and computing these redundant representations independently, however,
SOAR uses an orthogonality-amplified residual loss, which optimizes each
representation to compensate for cases where other representations perform
poorly. This drastically improves the overall index quality, resulting in
state-of-the-art ANN benchmark performance while maintaining fast indexing
times and low memory consumption.

SOAR 是一种新的数据索引技术，用于近似最近邻搜索。它通过使用正交扩增残差损失来优化每个表示，从而提高索引质量，同时保持快速索引时间和低内存消耗，从而获得最先进的 ANN 基准性能。

SOAR：改进的近似最近邻搜索索引化

SOAR: Improved Indexing for Approximate Nearest Neighbor Search

This paper is the recommended initial reading for a functional overview of
Soar, version 9.6. It includes an abstract overview of the architectural
structure of Soar including its processing, memories, learning modules, their
interfaces, and the representations of knowledge used by those modules. From
there it describes the processing supported by those modules, including
decision making, impasses and substates, procedure learning via chunking,
reinforcement learning, semantic memory, episodic memory, and spatial-visual
reasoning. It then reviews the levels of decision making and variety of
learning in Soar, and analysis of Soar as an architecture supporting general
human-level AI. Following the references is an appendix that contains short
descriptions of recent Soar agents and a glossary of the terminology we use in
describing Soar.

本文介绍了 Soar 的架构、处理方式、学习模块，以及决策制定、学习等方面的支持，分析了 Soar 作为支持通用人类水平 AI 的体系结构，并包含一部分近期 Soar 代理的简短描述和所使用术语的词汇表。

Soar 简介

Introduction to Soar

This is a detailed analysis and comparison of the ACT-R and Soar cognitive
architectures, including their overall structure, their representations of
agent data and metadata, and their associated processing. It focuses on working
memory, procedural memory, and long-term declarative memory. I emphasize the
commonalities, which are many, but also highlight the differences. I identify
the processes and distinct classes of information used by these architectures,
including agent data, metadata, and meta-process data, and explore the roles
that metadata play in decision making, memory retrievals, and learning.

本文对 ACT-R 和 Soar 的认知体系结构进行了详细分析和比较，包括它们的总体结构，对代理数据和元数据的表述，以及相关处理。重点关注工作记忆、程序记忆和长期陈述性记忆，强调了两者的共同点和差异，阐明了这些体系结构使用的信息进程和不同类别的信息，包括代理数据、元数据和元进程数据，并探讨了元数据在决策、内存检索和学习中所起的作用。

ACT-R 和 Soar 的分析和比较

An Analysis and Comparison of ACT-R and Soar

Adversarial training is a common approach to improving the robustness of deep
neural networks against adversarial examples. In this work, we propose a novel
regularization approach as an alternative. To derive the regularizer, we
formulate the adversarial robustness problem under the robust optimization
framework and approximate the loss function using a second-order Taylor series
expansion. Our proposed second-order adversarial regularizer (SOAR) is an upper
bound based on the Taylor approximation of the inner-max in the robust
optimization objective. We empirically show that the proposed method
significantly improves the robustness of networks against the $\ell_\infty$ and
$\ell_2$ bounded perturbations generated using cross-entropy-based PGD on
CIFAR-10 and SVHN.

本文提出了一种新颖的正则化方法 SOAR，它是基于强健优化架构中内向最大值的 Taylor 近似推导的上界，实验证明其在对抗样本的生成和鲁棒性上能够显著提高深度神经网络的性能。