23 citations · 39 across the 8 of their papers we have counts for
7 papers · 1 filter
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic
Nidhi Gowdra, Roopak Sinha, Stephen MacDonell +1
Convolutional Neural Networks (CNNs) such as ResNet-50, DenseNet-40 and ResNeXt-56 are severely over-parameterized, necessitating a consequent increase in the computational resourc…
Towards the statistical construction of hybrid development methods
Paolo Tell, Jil Klünder, Steffen Küpper +6
Hardly any software development process is used as prescribed by authors or standards. Regardless of company size or industry sector, a majority of project teams and companies use…
Examining and Mitigating Kernel Saturation in Convolutional Neural Networks using Negative Images
Nidhi Gowdra, Roopak Sinha, Stephen MacDonell
Neural saturation in Deep Neural Networks (DNNs) has been studied extensively, but remains relatively unexplored in Convolutional Neural Networks (CNNs). Understanding and alleviat…
Examining convolutional feature extraction using Maximum Entropy (ME) and Signal-to-Noise Ratio (SNR) for image classification
Nidhi Gowdra, Roopak Sinha, Stephen MacDonell
Convolutional Neural Networks (CNNs) specialize in feature extraction rather than function mapping. In doing so they form complex internal hierarchical feature representations, the…
Diagnosable-by-Design Model-Driven Development for IEC 61499 Industrial Cyber-Physical Systems
Barry Dowdeswell, Roopak Sinha, Stephen G. MacDonell
Integrating the design and creation of fault identification and diagnostic capabilities into Model-Driven Development methodologies is one approach to enhancing the resilience of I…
Employing Agent Beliefs during Fault Diagnosis for IEC 61499 Industrial Cyber-Physical Systems
Barry Dowdeswell, Roopak Sinha, Dennis Jarvis +2
We have come to rely on industrial-scale cyber-physical systems more and more to manage tasks and machinery in safety-critical situations. Efficient, reliable fault identification…