On the biological plausibility of orthogonal initialisation for solving gradient instability in deep neural networks

Abstract

Initialising the synaptic weights of artificial neural networks (ANNs) with orthogonal matrices is known to alleviate vanishing and exploding gradient problems. A major objection against such initialisation schemes is that they are deemed biologically implausible as they mandate factorization techniques that are difficult to attribute to a neurobiological process. This paper presents two initialisation schemes that allow a network to naturally evolve its weights to form orthogonal matrices, provides theoretical analysis that pre-training orthogonalisation always converges, and empirically confirms that the proposed schemes outperform randomly initialised recurrent and feedforward networks.

9 pages, 3 figures, to be published in ISCMI2022 conference proceedings

References in corpus (4)

• On the difficulty of training Recurrent Neural Networks
• The Loss Surfaces of Multilayer Networks
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
• Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible