Deep Learning
Inherent Weight Normalization in Stochastic Neural Networks
Georgios Detorakis, Sourav Dutta, Abhishek Khanna, Matthew Jerry, Suman Datta, Emre Neftci
Neural Information Processing Systems http://nips.cc/
Reinforced Continual Learning
Neural Information Processing Systems http://nips.cc/
Learning Representations by Maximizing Mutual Information Across Views
Philip Bachman, R Devon Hjelm, William Buchwalter
Neural Information Processing Systems http://nips.cc/
Supplementary Material StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on the Microcontroller Contents
However, TFLM's interpreter increases the performance overhead of the TinyML applications on MCUs. Unlike TFLM, StreamNet and MCUNetv2 replace the interpreter with a code generator. The system architecture of StreamNet contains the frontend and backend processing. Table 1 presents the data of StreamNet-2D. In Table 1, StreamNet achieves a geometric mean of 5.11X speedup TinyML models collected at the compile time to guide its auto-tuning framework.
A Retrieve-and-Edit Framework for Predicting Structured Outputs
Tatsunori B. Hashimoto, Kelvin Guu, Yonatan Oren, Percy S. Liang
Neural Information Processing Systems http://nips.cc/