Tuning Algorithms and Generators for Efficient Edge Inference

no code implementations • 31 Jul 2019 • Rawan Naous, Lazar Supic, Yoonhwan Kang, Ranko Sredojevic, Anish Singhani, Vladimir Stojanovic

A surge in artificial intelligence and autonomous technologies have increased the demand toward enhanced edge-processing capabilities.

Model Compression

MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression

no code implementations • 30 May 2018 • Lazar Supic, Rawan Naous, Ranko Sredojevic, Aleksandra Faust, Vladimir Stojanovic

Deep neural networks (DNNs) have become the state-of-the-art technique for machine learning tasks in various applications.

Neural Network Compression Quantization

Structured Deep Neural Network Pruning via Matrix Pivoting

no code implementations • 1 Dec 2017 • Ranko Sredojevic, Shaoyi Cheng, Lazar Supic, Rawan Naous, Vladimir Stojanovic

Deep Neural Networks (DNNs) are the key to the state-of-the-art machine vision, sensor fusion and audio/video signal processing.

Network Pruning Sensor Fusion