Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT

no code implementations • 26 Jul 2019 • Kartikeya Bhardwaj, Chingyi Lin, Anderson Sartor, Radu Marculescu

Therefore, we propose Network of Neural Networks (NoNN), a new distributed IoT learning paradigm that compresses a large pretrained 'teacher' deep network into several disjoint and highly-compressed 'student' modules, without loss of accuracy.

Image Classification Model Compression