Related papers: Hardware-Aware Neural Dropout Search for Reliable …

Multi-layer neural networks have lead to remarkable performance on many kinds of benchmark tasks in text, speech and image processing. Nonlinear parameter estimation in hierarchical models is known to be subject to overfitting and…

In convolutional neural network (CNN), dropout cannot work well because dropped information is not entirely obscured in convolutional layers where features are correlated spatially. Except randomly discarding regions or channels, many…

One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an over-parameterized…

Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights. However, such models face the challenge of Bayesian inference in a high-dimensional and usually…

The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning. Because the design space of deep learning software stacks and hardware accelerators is diverse…

Marginalising out uncertain quantities within the internal representations or parameters of neural networks is of central importance for a wide range of learning techniques, such as empirical, variational or full Bayesian methods. We set…

Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-of-distribution or adversarially generated points. In this…

While the role of Deep Neural Networks (DNNs) in a wide range of safety-critical applications is expanding, emerging DNNs experience massive growth in terms of computation power. It raises the necessity of improving the reliability of DNN…

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Bayesian neural networks (BNNs) have been long considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks. While they could capture more accurately the posterior…

Applying deep neural networks (DNNs) in mobile and safety-critical systems, such as autonomous vehicles, demands a reliable and efficient execution on hardware. Optimized dedicated hardware accelerators are being developed to achieve this.…

Deep learning has achieved remarkable success in the field of bearing fault diagnosis. However, this success comes with larger models and more complex computations, which cannot be transferred into industrial fields requiring models to be…

While embedded FPGAs are attractive platforms for DNN acceleration on edge-devices due to their low latency and high energy efficiency, the scarcity of resources of edge-scale FPGA devices also makes it challenging for DNN deployment. In…

Recent advances in algorithm-hardware co-design for deep neural networks (DNNs) have demonstrated their potential in automatically designing neural architectures and hardware designs. Nevertheless, it is still a challenging optimization…

This paper investigates neuron dropout as a post-processing bias mitigation for deep neural networks (DNNs). Neural-driven software solutions are increasingly applied in socially critical domains with significant fairness implications.…

We explore the utility of information contained within a dropout based Bayesian neural network (BNN) for the task of detecting out of distribution (OOD) data. We first show how previous attempts to leverage the randomized embeddings induced…

While deep neural networks have become the go-to approach in computer vision, the vast majority of these models fail to properly capture the uncertainty inherent in their predictions. Estimating this predictive uncertainty can be crucial,…

In recent years deep learning algorithms have shown extremely high performance on machine learning tasks such as image classification and speech recognition. In support of such applications, various FPGA accelerator architectures have been…

When trained as generative models, Deep Learning algorithms have shown exceptional performance on tasks involving high dimensional data such as image denoising and super-resolution. In an increasingly connected world dominated by mobile and…

In recent years, Convolutional Neural Networks (ConvNets) have become an enabling technology for a wide range of novel embedded Artificial Intelligence systems. Across the range of applications, the performance needs vary significantly,…