“I'd like to offer a somewhat contrasting viewpoint (although this might not sit well with people): deep nets aren't AGI, but they're pretty damn good. There's mounting evidence that they learn similar to how we do, at least in vision; https://arxiv.org/abs/1706.08606 and https://www.nature.com/articles/srep27755 There's quite a few others but these were …”
Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
Deep neural networks (DNNs) have achieved unprecedented performance on a wide range of complex tasks, rapidly outpacing our understanding of the nature of their solutions. This has caused a recent surge of interest in methods for rendering modern neural systems more interpretable. In this work, we propose to address the interpretability problem in modern DNNs using the rich history of problem descriptions, theories and experimental methods developed by cognitive psychologists to study the human mind. To explore the potential value of these tools, we chose a well-established analysis from developmental psychology that explains how children learn word labels for objects, and applied that analysis to DNNs. Using datasets of stimuli inspired by the original cognitive psychology experiments, we find that state-of-the-art one shot learning models trained on ImageNet exhibit a similar bias to that observed in humans: they prefer to categorize objects according to shape rather than color. The magnitude of this shape bias varies greatly among architecturally identical, but differently seeded models, and even fluctuates within seeds throughout training, despite nearly equivalent classification performance. These results demonstrate the capability of tools from cognitive psychology for exposing hidden computational properties of DNNs, while concurrently providing us with a computational model for human word learning.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Yeah, I looked it up yesterday and saw that artificial cognition is a thing, though I must say I am not a fan and I certainly hope this term does not catch. We are already knee deep in bad terminology because of artificial intelligence (“intelligence” already being extremely problematic even with out the “artificial” qualifier in psychology) and machine l…”
- Cognitive Psychology for Deep Neural Networks (DeepMind) ↗aaronyy · 2017-07-04 · 2 分