How to Train Unstable Looped Tensor Network

no code implementations • 5 Mar 2022 • Anh-Huy Phan, Konstantin Sobolev, Dmitry Ermilov, Igor Vorona, Nikolay Kozyrskiy, Petr Tichavsky, Andrzej Cichocki

This motivates using a hybrid model of CPD and TKD, a decomposition with multiple Tucker models with small core tensor, known as block term decomposition (BTD).

Tensor Decomposition Tensor Networks

QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks

no code implementations • CVPR 2021 • Vladimir Kryzhanovskiy, Gleb Balitskiy, Nikolay Kozyrskiy, Aleksandr Zuruev

Modern deep neural networks (DNNs) cannot be effectively used in mobile and embedded devices due to strict requirements for computational complexity, memory, and power consumption.

Parameter Prediction Quantization +1

CNN Acceleration by Low-rank Approximation with Quantized Factors

no code implementations • 16 Jun 2020 • Nikolay Kozyrskiy, Anh-Huy Phan

The modern convolutional neural networks although achieve great results in solving complex computer vision tasks still cannot be effectively used in mobile and embedded devices due to the strict requirements for computational complexity, memory and power consumption.

Quantization