6 papers
Simple Regularisation for Uncertainty-Aware Knowledge Distillation
Martin Ferianc, Miguel Rodrigues
Considering uncertainty estimation of modern neural networks (NNs) is one of the most important steps towards deploying machine learning systems to meaningful real-world applicatio…
Optimizing Bayesian Recurrent Neural Networks on an FPGA-based Accelerator
Martin Ferianc, Zhiqiang Que, Hongxiang Fan +2
Neural networks have demonstrated their outstanding performance in a wide range of tasks. Specifically recurrent architectures based on long-short term memory (LSTM) cells have man…
ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation
Martin Ferianc, Divyansh Manocha, Hongxiang Fan +1
Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deploy…
On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks
Martin Ferianc, Partha Maji, Matthew Mattina +1
Bayesian neural networks (BNNs) are making significant progress in many research areas where decision-making needs to be accompanied by uncertainty estimation. Being able to quanti…
VINNAS: Variational Inference-based Neural Network Architecture Search
Martin Ferianc, Hongxiang Fan, Miguel Rodrigues
In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accurac…
Improving Performance Estimation for FPGA-based Accelerators for Convolutional Neural Networks
Martin Ferianc, Hongxiang Fan, Ringo S. W. Chu +2
Field-programmable gate array (FPGA) based accelerators are being widely used for acceleration of convolutional neural networks (CNNs) due to their potential in improving the perfo…