Doctor of Crosswise: Reducing Over-parametrization in Neural Networks
This addresses the issue of reducing computational and memory overhead in neural networks for AI practitioners, but appears incremental as it builds on existing deep learning frameworks.
The paper tackles the problem of over-parametrization in neural networks by proposing a new architecture called Doctor of Crosswise, which introduces an operand for rapid computation using learned weights, though no concrete results or numbers are provided.
Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning that leverages learned weights. The formalism is described in detail providing both an accurate elucidation of the mechanics and the theoretical implications.