# No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference

Source: [No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference](<https://www.sota2.com/research/paper/68fa64e31e209131cea07214>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:13:58.604Z

Authors: Shumeet Baluja, David Marwood, Michele Covell, Nick Johnston

Published: 2018-09-24T22:29:24.000Z

## Abstract

For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memory/power resources used during inference. Completely avoiding inference-time floating-point operations is one of the simplest ways to design networks for these highly-constrained environments. By discretizing both our in-network non-linearities and our network weights, we can move to simple, compact networks without floating point operations, without multiplications, and avoid all non-linear function computations. Our approach allows us to explore the spectrum of possible networks, ranging from fully continuous versions down to networks with bi-level weights and activations. Our results show that discretization can be done without loss of performance and that we can train a network that will successfully operate without floating-point, without multiplication, and with less RAM on both regression tasks (auto encoding) and multi-class classification tasks (ImageNet). The memory needed to deploy our discretized networks is less than one third of the equivalent architecture that does use floating-point operations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1809.09244>)

[PDF](<https://arxiv.org/pdf/1809.09244.pdf>)
