.png){kind=icon}
返回
Why concepts are (probably) vectors
.png){kind=icon}
PRE
AI
DOI：10.1016/j.tics.2024.06.011.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
For decades, cognitive scientists have debated what kind of representation might characterize human concepts. Whatever the format of the representation, it must allow for the computation of varied properties, including similarities, features, categories, definitions, and relations. It must also support the development of theories, ad hoc categories, and knowledge of procedures. Here, we discuss why vector- based representations provide a compelling account that can meet all these needs while being plausibly encoded into neural architectures. This view has become especially promising with recent advances in both large language models and vector symbolic architectures. These innovations show how vectors can handle many properties traditionally thought to be out of reach for neural models, including compositionality, definitions, structures, and symbolic computational processes.
Keyword:
COGNITIVE ARCHITECTURE
REPRESENTATIONS
MODEL
ACQUISITION
COMPLEXITY
KNOWLEDGE
PROGRAMS
LANGUAGE
MEMORY
期刊
IF:
17.2
论文数:
3.6K
被引数:
3.5W
机构
引用论文
Clinical Efficacy and Safety of Oral Decitabine/Cedazuridine in 133 Patients with Myelodysplastic Syndromes (MDS) and Chronic Myelomonocytic Leukemia (CMML).png)
Blood
OAAI
BloodIF0
OAAI分享收藏Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors超维计算: 高维随机向量分布式表示计算简介
PREAI
分享收藏
分享收藏
查看更多内容