Learning low-precision neural networks without Straight-Through Estimator(STE)

Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs

Measuring scheduling efficiency of RNNs for NLP applications

FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning

Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications

Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision

Mobile Machine Learning Hardware at Arm: A Systems-on-Chip (SoC) Perspective

Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning

SCALE-Sim: Systolic CNN Accelerator Simulator

Efficient and Robust Machine Learning for Real-World Systems