3 papers
cs.LG2026
Structure and Scale in Simplicial Sequence Modelling
Matthew Farrugia-Roberts
Modern large-scale deep learning exhibits two striking empirical phenomena: behavioural scaling laws (predictable performance gains with increasing scale) and emergent mechanisms (…
cs.NE2023
Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks
Matthew Farrugia-Roberts
Understanding the learning process of artificial neural networks requires clarifying the structure of the parameter space within which learning takes place. A neural network parame…
cs.LG2023
Proximity to Losslessly Compressible Parameters
Matthew Farrugia-Roberts
To better understand complexity in neural networks, we theoretically investigate the idealised phenomenon of lossless network compressibility, whereby an identical function can be…