In this paper I present a practical approach for coupling machine learning
(ML) algorithms with knowledge bases (KB) ontology formalism. The lack of
availability of prior knowledge in dynamic scenarios is without doubt a major
barrier for scalable machine intelligence. My view of the interaction between
the two tiers intelligence is based on the idea that when knowledge is not
readily available at the knowledge base tier, more knowledge can be extracted
from the other tier, which has access to trained models from machine learning
algorithms. To analyse this hypothesis, I create two experiments based on
different datasets, which are related directly to risk-awareness of autonomous
systems, analysed by different machine learning algorithms (namely; multi-layer
feedforward backpropagation, Naive Bayes, and J48 decision tree). My analysis
shows that the two-tiers intelligence approach for coupling ML and KB is
computationally valid and the time complexity of the algorithms during the
robot mission is linear with the size of the data and knowledge.

本文提出了一种实用的方法，将机器学习算法与知识库本体形式结合。通过两个基于不同数据集的实验，分析了自主系统的风险意识，应用了多层前馈反向传播、朴素贝叶斯和 J48 决策树等机器学习算法。研究表明，将机器学习和知识库进行二层智能耦合是可行的，算法的时间复杂度与数据和知识的大小成线性关系。

机器学习与本体论在机器人应用中的耦合

Coupling Machine Learning with Ontology for Robotics Applications

The modern pervasiveness of large-scale deep neural networks (NNs) is driven
by their extraordinary performance on complex problems but is also plagued by
their sudden, unexpected, and often catastrophic failures, particularly on
challenging scenarios. Existing algorithms that provide risk-awareness to NNs
are complex and ad-hoc. Specifically, these methods require significant
engineering changes, are often developed only for particular settings, and are
not easily composable. Here we present capsa, a framework for extending models
with risk-awareness. Capsa provides a methodology for quantifying multiple
forms of risk and composing different algorithms together to quantify different
risk metrics in parallel. We validate capsa by implementing state-of-the-art
uncertainty estimation algorithms within the capsa framework and benchmarking
them on complex perception datasets. We demonstrate capsa's ability to easily
compose aleatoric uncertainty, epistemic uncertainty, and bias estimation
together in a single procedure, and show how this approach provides a
comprehensive awareness of NN risk.

通过扩展模型实现对风险的认知，并利用不同算法量化不同风险指标，以此提供深度神经网络的全面风险感知。

Capsa：深度神经网络风险量化的统一框架

Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks

Risk-aware urban localization with the Global Navigation Satellite System
(GNSS) remains an unsolved problem with frequent misdetection of the user's
street or side of the street. Significant advances in 3D map-aided GNSS use
grid-based GNSS shadow matching alongside AI-driven line-of-sight (LOS)
classifiers and server-based processing to improve localization accuracy,
especially in the cross-street direction. Our prior work introduces a new
paradigm for shadow matching that proposes set-valued localization with
computationally efficient zonotope set representations. While existing
literature improved accuracy and efficiency, the current state of shadow
matching theory does not address the needs of risk-aware autonomous systems. We
extend our prior work to propose Mosaic Zonotope Shadow Matching (MZSM) that
employs a classifier-agnostic polytope mosaic architecture to provide
risk-awareness and certifiable guarantees on urban positioning. We formulate a
recursively expanding binary tree that refines an initial location estimate
with set operations into smaller polytopes. Together, the smaller polytopes
form a mosaic. We weight the tree branches with the probability that the user
is in line of sight of the satellite and expand the tree with each new
satellite observation. Our method yields an exact shadow matching distribution
from which we guarantee uncertainty bounds on the user localization. We perform
high-fidelity simulations using a 3D building map of San Francisco to validate
our algorithm's risk-aware improvements. We demonstrate that MZSM provides
certifiable guarantees across varied data-driven LOS classifier accuracies and
yields a more precise understanding of the uncertainty over existing methods.
We validate that our tree-based construction is efficient and tractable,
computing a mosaic from 14 satellites in 0.63 seconds and growing quadratically
in the satellite number.

本文提出了一种利用聚合体拼贴结构实现的阴影匹配算法，从而为城市定位提供风险感知和可证明的保证。

在恶劣城市环境中进行风险感知自主定位的 Mosaic Zonotope Shadow 匹配

Mosaic Zonotope Shadow Matching for Risk-Aware Autonomous Localization in Harsh Urban Environments

Trading markets represent a real-world financial application to deploy
reinforcement learning agents, however, they carry hard fundamental challenges
such as high variance and costly exploration. Moreover, markets are inherently
a multiagent domain composed of many actors taking actions and changing the
environment. To tackle these type of scenarios agents need to exhibit certain
characteristics such as risk-awareness, robustness to perturbations and low
learning variance. We take those as building blocks and propose a family of
four algorithms. First, we contribute with two algorithms that use risk-averse
objective functions and variance reduction techniques. Then, we augment the
framework to multi-agent learning and assume an adversary which can take over
and perturb the learning process. Our third and fourth algorithms perform well
under this setting and balance theoretical guarantees with practical use.
Additionally, we consider the multi-agent nature of the environment and our
work is the first one extending empirical game theory analysis for multi-agent
learning by considering risk-sensitive payoffs.

提出了一系列用于对付高波动性、高代价探索、多智能体交互等具有挑战性的贸易市场的强化学习算法，并将其应用于多智能体环境。这些算法不仅考虑风险意识、扰动下的鲁棒性和低学习方差，还进行了实证博弈理论的扩展。