4 papers · 1 filter
Empirical Minimal-Realisation Compression of Deep Neural Networks via Controllability-Observability Tests
Anis Hamadouche, Amir Hussain
Deep neural networks often contain substantial hidden-state redundancy, but most compression methods operate directly on weights, neurons, or quantised representations without expl…
Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic
Anis Hamadouche, Amir Hussain
Low-precision neural networks are attractive for resource-constrained hardware, but fixed-point arithmetic introduces failure modes that are often hidden by idealised quantisation…
Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer
Anis Hamadouche, Mathini Sellathurai
This paper investigates communication-efficient neural network transmission by exploiting structured symmetry constraints in convolutional kernels. Instead of transmitting all mode…
Stochastic Delayed Dynamics of Rumor Propagation with Awareness and Fact-Checking
Lamia Alyami, Anis Hamadouche, Amir Hussain
This paper presents a stochastic delayed differential model for rumor propagation during infodemic that incorporates human behavioral response, public skepticism and fact-checking…