Approximate Multiplier Induced Error Propagation in Deep Neural Networks Article Swipe

MAKE IMPACT

Alahakoon, A. M. H. H. , Saadat, Hassaan , Jayasinghe, Darshana , Parameswaran, Sri · YOU? · · 2025 · Open Access ·

Deep Neural Networks (DNNs) rely heavily on dense arithmetic operations, motivating the use of Approximate Multipliers (AxMs) to reduce energy consumption in hardware accelerators. However, a rigorous mathematical characterization of how AxMs error distributions influence DNN accuracy remains underdeveloped. This work presents an analytical framework that connects the statistical error moments of an AxM to the induced distortion in General Matrix Multiplication (GEMM). Using the Frobenius norm of the resulting error matrix, we derive a closed form expression for practical DNN dimensions that demonstrates the distortion is predominantly governed by the multiplier mean error (bias). To evaluate this model in realistic settings, we incorporate controlled error injection into GEMM and convolution layers and examine its effect on ImageNet scale networks. The predicted distortion correlates strongly with the observed accuracy degradation, and an error configurable AxM case study implemented on an FPGA further confirms the analytical trends. By providing a lightweight alternative to behavioral or hardware level simulations, this framework enables rapid estimation of AxM impact on DNN inference quality.

Type

article

Landing Page

http://arxiv.org/abs/2512.06537

PDF

https://arxiv.org/pdf/2512.06537

OA Status

green

OpenAlex ID

https://openalex.org/W7113915478

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W7113915478

Canonical identifier for this work in OpenAlex

Title

Approximate Multiplier Induced Error Propagation in Deep Neural Networks

Work title

Type

article

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-12-06

Full publication date if available

Authors

Alahakoon, A. M. H. H., Saadat, Hassaan, Jayasinghe, Darshana, Parameswaran, Sri

List of authors in order

Landing page

https://arxiv.org/abs/2512.06537

Publisher landing page

PDF URL

https://arxiv.org/pdf/2512.06537

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2512.06537

Direct OA link when available

Concepts

Multiplier (economics), Artificial neural network, Computer science, Inference, Algorithm, Multiplication (music), Propagation of uncertainty, Distortion (music), Approximation error, Norm (philosophy), Error detection and correction, Convolution (computer science), Mean squared prediction error, Backpropagation, Deep neural networks, Mean squared error, Energy consumption, Matrix (chemical analysis), Matrix norm, Mathematics, Round-off error, Matrix representation, Artificial intelligence, Convolutional neural network, Approximation theory, Field-programmable gate array, Computation, Lagrange multiplier, Adder, Arithmetic, Energy (signal processing), Matrix multiplication, Scale (ratio), Error analysis

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Full payload