3 papers
cs.LG2026
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…
cs.LG2026
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…
cs.SD2026
Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
Anis Hamadouche, Haifeng Luo, Mathini Sellathurai +2
Real-time audio-visual speech enhancement (AVSE) is a key enabler for immersive and interactive multimedia services, yet its performance is tightly constrained by network latency,…