A 47.4µJ/epoch Trainable Deep Convolutional Neural Network Accelerator for In-Situ Personalization on Smart Devices
暂无分享,去创建一个
Seungkyu Choi | Yeongjae Choi | Jaehyeong Sim | Hyeonuk Kim | Lee-Sup Kim | Myeonggu Kang | L. Kim | Seungkyu Choi | Hyeonuk Kim | Myeonggu Kang | Yeongjae Choi | Jaehyeong Sim
[1] Joel Silberman,et al. A Scalable Multi- TeraOPS Deep Learning Processor Core for AI Trainina and Inference , 2018, 2018 IEEE Symposium on VLSI Circuits.
[2] Joel Emer,et al. Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks , 2016, CARN.
[3] Meng-Fan Chang,et al. Sticker: A 0.41-62.1 TOPS/W 8Bit Neural Network Processor with Multi-Sparsity Compatible Convolution Arrays and Online Tuning Acceleration for Fully Connected Layers , 2018, 2018 IEEE Symposium on VLSI Circuits.
[4] Jing Wang,et al. In-Situ AI: Towards Autonomous and Incremental Deep Learning for IoT Systems , 2018, 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA).
[5] Hoi-Jun Yoo,et al. 7.7 LNPU: A 25.3TFLOPS/W Sparse Deep-Neural-Network Learning Processor with Fine-Grained Mixed Precision of FP8-FP16 , 2019, 2019 IEEE International Solid- State Circuits Conference - (ISSCC).
[6] Lee-Sup Kim,et al. TrainWare: A Memory Optimized Weight Update Architecture for On-Device Convolutional Neural Network Training , 2018, ISLPED.
[7] Hoi-Jun Yoo,et al. UNPU: An Energy-Efficient Deep Neural Network Accelerator With Fully Variable Weight Bit Precision , 2019, IEEE Journal of Solid-State Circuits.