Search Results for author: Lukas Sekanina

Found 8 papers, 3 papers with code

Evolutionary Algorithms in Approximate Computing: A Survey

no code implementations16 Aug 2021 Lukas Sekanina

The evolutionary approximation has been applied at all levels of design abstraction and in many different applications.

Evolutionary Algorithms Neural Architecture Search

Evolutionary Neural Architecture Search Supporting Approximate Multipliers

no code implementations28 Jan 2021 Michal Pinos, Vojtech Mrazek, Lukas Sekanina

During the NAS process, a suitable CNN architecture is evolved together with approximate multipliers to deliver the best trade-offs between the accuracy, network size, and power consumption.

Evolutionary Algorithms Neural Architecture Search

Adaptive Verifiability-Driven Strategy for Evolutionary Approximation of Arithmetic Circuits

no code implementations5 Mar 2020 Milan Ceska, Jiri Matyas, Vojtech Mrazek, Lukas Sekanina, Zdenek Vasicek, Tomas Vojnar

We present a novel approach for designing complex approximate arithmetic circuits that trade correctness for power consumption and play important role in many energy-aware applications.

TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPU

1 code implementation21 Feb 2020 Filip Vaverka, Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina

In order to address this issue, we propose an efficient emulation method for approximate circuits utilized in a given DNN accelerator which is emulated on GPU.

Optimizing Convolutional Neural Networks for Embedded Systems by Means of Neuroevolution

no code implementations15 Oct 2019 Filip Badan, Lukas Sekanina

Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity.

Classification General Classification +1

ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining

1 code implementation11 Jun 2019 Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina, Muhammad Abdullah Hanif, Muhammad Shafique

A suitable approximate multiplier is then selected for each computing element from a library of approximate multipliers in such a way that (i) one approximate multiplier serves several layers, and (ii) the overall classification error and energy consumption are minimized.

Multiobjective Optimization

Automated Circuit Approximation Method Driven by Data Distribution

no code implementations11 Mar 2019 Zdenek Vasicek, Vojtech Mrazek, Lukas Sekanina

We propose an application-tailored data-driven fully automated method for functional approximation of combinational circuits.

General Classification

autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components

2 code implementations22 Feb 2019 Vojtech Mrazek, Muhammad Abdullah Hanif, Zdenek Vasicek, Lukas Sekanina, Muhammad Shafique

Because these libraries contain from tens to thousands of approximate implementations for a single arithmetic operation it is intractable to find an optimal combination of approximate circuits in the library even for an application consisting of a few operations.

Cannot find the paper you are looking for? You can Submit a new open access paper.