EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
This work addresses the need for more efficient deep learning deployments on low-power, memory-restricted devices, offering an incremental improvement by redesigning operations rather than introducing a new paradigm.
The paper tackles the problem of efficient deep learning inference on edge devices by proposing EuclidNet, a compression method that replaces multiplication with Euclidean distance, achieving comparable performance to conventional models under various transformations and noise scenarios.
With the advent of deep learning application on edge devices, researchers actively try to optimize their deployments on low-power and restricted memory devices. There are established compression method such as quantization, pruning, and architecture search that leverage commodity hardware. Apart from conventional compression algorithms, one may redesign the operations of deep learning models that lead to more efficient implementation. To this end, we propose EuclidNet, a compression method, designed to be implemented on hardware which replaces multiplication, $xw$, with Euclidean distance $(x-w)^2$. We show that EuclidNet is aligned with matrix multiplication and it can be used as a measure of similarity in case of convolutional layers. Furthermore, we show that under various transformations and noise scenarios, EuclidNet exhibits the same performance compared to the deep learning models designed with multiplication operations.