[논문리뷰] μLayer: Low Latency On-Device Inference Using Cooperative Single-Layer Acceleration and Processor-Friendly Quantization 요약

[주의] 개인 공부를 위해 쓴 글이기 때문에 주관적인 내용은 물론, 쓰여진 정보가 틀린 것일 수도 있습니다!

피드백 부탁드립니다. (- -)(_ _) 꾸벅

 

https://yonsei.pure.elsevier.com/en/publications/%C2%B5layer-low-latency-on-device-inference-using-cooperative-single-l

µLayer: Low latency on-device inference using cooperative single-layer acceleration and processor-friendly quantization

---

[ 1. Introduction ] 

 

---

[ 2. BackGround ]

 

---

[ 3. Cooperative Single-Layer Acceleration ]

 

---

[ 4. Processor-Friendly Quantization ] 

 

---

[ 5. Branch Distribution ]

 

---

[ 6. Implementation ]

---

[ 7. Experiment ]

---