Faculty of Information Technology, University of Jyväskylä, 40014 Jyväskylän yliopisto, Finland
Neural Comput. 2021 Dec 15;34(1):255-290. doi: 10.1162/neco_a_01449.
Machine learning is a good tool to simulate human cognitive skills as it is about mapping perceived information to various labels or action choices, aiming at optimal behavior policies for a human or an artificial agent operating in the environment. Regarding autonomous systems, objects and situations are perceived by some receptors as divided between sensors. Reactions to the input (e.g., actions) are distributed among the particular capability providers or actuators. Cognitive models can be trained as, for example, neural networks. We suggest training such models for cases of potential disabilities. Disability can be either the absence of one or more cognitive sensors or actuators at different levels of cognitive model. We adapt several neural network architectures to simulate various cognitive disabilities. The idea has been triggered by the "coolability" (enhanced capability) paradox, according to which a person with some disability can be more efficient in using other capabilities. Therefore, an autonomous system (human or artificial) pretrained with simulated disabilities will be more efficient when acting in adversarial conditions. We consider these coolabilities as complementary artificial intelligence and argue on the usefulness if this concept for various applications.
机器学习是一种很好的工具，可以模拟人类认知技能，因为它是将感知信息映射到各种标签或动作选择上，旨在为在环境中运行的人类或人工智能代理制定最优行为策略。对于自主系统，对象和情况通过一些传感器被划分为不同的接收器感知。对输入的反应（例如，动作）分布在特定的能力提供者或执行器中。认知模型可以作为神经网络进行训练。我们建议为潜在残疾情况训练这些模型。残疾可以是认知模型不同级别上的一个或多个认知传感器或执行器的缺失。我们适应了几种神经网络架构来模拟各种认知障碍。这个想法是由“冷却能力”（增强能力）悖论引发的，根据这个悖论，有某种残疾的人可以更有效地利用其他能力。因此，经过模拟残疾训练的自主系统（人类或人工智能）在对抗条件下的行动将更加高效。我们将这些冷却能力视为人工智能的补充，并就该概念在各种应用中的有用性进行了论证。
