activity
20182020
most citedDeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression

8 citations · 9 across the 3 of their papers we have counts for

collaborators

8 papers

cs.AR2020

FantastIC4: A Hardware-Software Co-Design Approach for Efficiently Running 4bit-Compact Multilayer Perceptrons

Simon Wiedemann, Suhas Shivapakash, Pablo Wiedemann +4

With the growing demand for deploying deep learning models to the "edge", it is paramount to develop techniques that allow to execute state-of-the-art models within very tight and…

cs.LG20201 cited

Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training

Simon Wiedemann, Temesgen Mehari, Kevin Kepp +1

Deep Neural Networks are successful but highly computationally expensive learning systems. One of the main sources of time and energy drains is the well known backpropagation (back…

cs.LG2019

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning

Seul-Ki Yeom, Philipp Seegerer, Sebastian Lapuschkin +4

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to r…

cs.LG20198 cited

DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression

Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage +9

We present DeepCABAC, a novel context-adaptive binary arithmetic coder for compressing deep neural networks. It quantizes each weight parameter by minimizing a weighted rate-distor…

cs.LG2019

Robust and Communication-Efficient Federated Learning from Non-IID Data

Felix Sattler, Simon Wiedemann, Klaus-Robert Müller +1

Federated Learning allows multiple parties to jointly train a deep learning model on their combined data, without any of the participants having to reveal their local data to a cen…

cs.LG2018

Entropy-Constrained Training of Deep Neural Networks

Simon Wiedemann, Arturo Marban, Klaus-Robert Müller +1

We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the en…