Approximate Multiplier Induced Error Propagation in Deep Neural Networks
By: A. M. H. H. Alahakoon , Hassaan Saadat , Darshana Jayasinghe and more
Potential Business Impact:
Makes computer chips use less power for AI.
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.
Similar Papers
Low Power Approximate Multiplier Architecture for Deep Neural Networks
Hardware Architecture
Makes AI chips use less power, work better.
MMA-Sim: Bit-Accurate Reference Model of Tensor Cores and Matrix Cores
Hardware Architecture
Fixes computer math errors in AI programs.
The Cambrian Explosion of Mixed-Precision Matrix Multiplication for Quantized Deep Learning Inference
Computation and Language
Makes computers do math faster for AI.