论文标题
深度学习高级认知的归纳偏见
Inductive Biases for Deep Learning of Higher-Level Cognition
论文作者
论文摘要
一个令人着迷的假设是，人类和动物智力可以通过一些原则（而不是启发式方法的百科全书清单）来解释。如果这个假设是正确的，我们可以更容易地理解自己的智能并建造智能机器。就像物理学一样，原理本身就不足以预测大脑等复杂系统的行为，并且可能需要大量计算来模拟类似人类的智力。这一假设将表明，研究人类和动物所剥削的归纳偏见可以帮助阐明这些原则，并为AI研究和神经科学理论提供灵感。深度学习已经利用了几种关键的归纳偏见，这项工作考虑了更大的列表，重点关注的是大多数涉及更高级别和顺序有意识的处理的列表。澄清这些特定原则的目的是，它们有可能帮助我们建立从人类的能力中受益于灵活的分布和系统概括的能力的AI系统，目前，这是一个在最新的机器学习和人类智能之间存在巨大差距的领域。
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopedic list of heuristics). If that hypothesis was correct, we could more easily both understand our own intelligence and build intelligent machines. Just like in physics, the principles themselves would not be sufficient to predict the behavior of complex systems like brains, and substantial computation might be needed to simulate human-like intelligence. This hypothesis would suggest that studying the kind of inductive biases that humans and animals exploit could help both clarify these principles and provide inspiration for AI research and neuroscience theories. Deep learning already exploits several key inductive biases, and this work considers a larger list, focusing on those which concern mostly higher-level and sequential conscious processing. The objective of clarifying these particular principles is that they could potentially help us build AI systems benefiting from humans' abilities in terms of flexible out-of-distribution and systematic generalization, which is currently an area where a large gap exists between state-of-the-art machine learning and human intelligence.
