Segmented Angular Pre-Processing for Accurate and Efficient In-Memory Vector Similarity Search

Vector similarity search (VSS) is a fundamental operation in modern AI applications, including few-shot learning (FSL) and approximate nearest neighbor search (ANNS). Cosine similarity is widely regarded as the optimal metric for VSS. However, VSS incurs substantial energy and computational overhead...

Celý popis

Podrobná bibliografia

Vydané v:	2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7
Hlavní autori:	Huang, Chi-Tse, Wang, Jen-Chieh, Cheng, Hsiang-Yun, Wu, An-Yeu Andy
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 22.06.2025
Predmet:	Accuracy Encoding Energy efficiency Hamming distances Hardware Measurement Nearest neighbor methods Quantization (signal) Simulation Vectors
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!