← Back to all news
arXiv Machine Learning By Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe

Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers

Read the original on arXiv Machine Learning →

Deep Microcompression (DMC) is a hardware‑aware pipeline that combines structured pruning, quantization‑aware training, and fixed‑length bit‑packing to enable deep learning inference on bare‑metal microcontrollers. The method achieves a 55.8× weight compression on LeNet‑5 while maintaining 98.77% accuracy, and produces a dependency‑free C library with deterministic latency. On the RP2040 Cortex‑M0+ microcontroller, DMC cuts binary size threefold compared to TensorFlow Lite while matching its accuracy, and it is the first documented deployment of a standard CNN on the 2 KB SRAM ATmega328P.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 28

Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted Algorithms

The paper presents a PyTorch-based framework for designing and optimizing binarized neural networks, incorporating freezing and pruning mechanisms. It introduces a novel pruning method that uses a global weighting scheme to assess parameter importance across abstraction levels, achieving a 70% pruning rate on VGG11 without sacrificing accuracy—outperforming existing binarized pruning results of 41%. The framework facilitates rapid, reproducible evaluation and prototyping of state‑of‑the‑art binarized network techniques.

By Roan Rubiales, Jean Pierre David
efficiencybenchmarks
More like this →
arXiv Machine Learning
Oct 5

16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs

The paper introduces W16A16, a 16‑bit precision quantization method for convolutional neural networks aimed at microcontroller units. On the Armv7E‑M architecture, W16A16 delivers faster inference speeds and lower energy consumption than existing quantization schemes while reducing quantization errors by roughly tenfold compared to 8‑bit approaches. The authors analyze the MCU architecture, explain why 16‑bit operations yield performance gains, and evaluate empirical errors and resource usage across regression and classification tasks.

By Rui Liu, Benjamin Paa{\ss}en
efficiency
More like this →