Details

Autor(en) / Beteiligte

• Li, Haitong
• Chen, Wei-Chen
• Levy, Akash
• Wang, Ching-Hua
• Wang, Hongjie
• Chen, Po-Han
• Wan, Weier
• Khwa, Win-San
• Chuang, Harry
• Chih, Y.-D.
• Chang, Meng-Fan
• Wong, H.-S. Philip
• Raina, Priyanka

Titel

SAPIENS: A 64-kb RRAM-Based Non-Volatile Associative Memory for One-Shot Learning and Inference at the Edge

Ist Teil von

• IEEE transactions on electron devices, 2021-12, Vol.68 (12), p.6637-6643

Ort / Verlag

New York: IEEE

Erscheinungsjahr

2021

Quelle

IEEE Electronic Library Online

Beschreibungen/Notizen

• Learning from a few examples (one/few-shot learning) on the fly is a key challenge for on-device machine intelligence. We present the first chip-level demonstration of one-shot learning with Stanford Associative memory for Programmable, Integrated Edge iNtelligence via life-long learning and Search (SAPIENS), a resistive random access memory (RRAM)-based non-volatile associative memory (AM) chip that serves as the backend for memory-augmented neural networks (MANNs). The 64-kb fully integrated RRAM-CMOS AM chip performs long-term feature embedding and retrieval, demonstrated on a 32-way one-shot learning task on the Omniglot dataset. Using only one example per class for 32 unseen classes during on-chip learning, SAPIENS achieves 79% measured inference accuracy on Omniglot, comparable to edge software model accuracy using five-level quantization (82%). It achieves an energy efficiency of 118 GOPS/W at 200 MHz for in-memory L1 distance computation and prediction. Multi-bank measurements on the same chip show that increasing the capacity from three banks (24 kb) to eight banks (64 kb) improves the chip accuracy from 73.5% to 79%, while minimizing the accuracy excursion due to bank-to-bank variability.