Pruning Increases Orderedness in Recurrent Computation
This work addresses the problem of understanding inductive biases in neural networks for AI researchers, but it is incremental as it builds on existing pruning and recurrent network concepts.
The study tackled the role of directionality as an inductive bias in neural networks by showing that pruning can induce topological ordering in recurrent circuits without performance loss, achieving greater ordering across random seeds.
Inspired by the prevalence of recurrent circuits in biological brains, we investigate the degree to which directionality is a helpful inductive bias for artificial neural networks. Taking directionality as topologically-ordered information flow between neurons, we formalise a perceptron layer with all-to-all connections (mathematically equivalent to a weight-tied recurrent neural network) and demonstrate that directionality, a hallmark of modern feed-forward networks, can be induced rather than hard-wired by applying appropriate pruning techniques. Across different random seeds our pruning schemes successfully induce greater topological ordering in information flow between neurons without compromising performance, suggesting that directionality is not a prerequisite for learning, but may be an advantageous inductive bias discoverable by gradient descent and sparsification.