Deep Microcompression enables the first documented deployment of a standard CNN on the ATmega328P, a device constrained to 2KB SRAM, previously considered infeasible for CNN inference.
Abstract
This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers. DMC integrates structured pruning, quantization-aware training, and fixed-length bit-packing to achieve a 55.8$\times$ weight compression ratio on LeNet-5 (98.77\% accuracy), generating a dependency-free C library with deterministic latency. On the RP2040 (Cortex-M0+), DMC reduces binary size by 3$\times$ versus TensorFlow Lite while matching its accuracy. Critically, DMC enables the first documented deployment of a standard CNN on the ATmega328P, a device constrained to 2KB SRAM, previously considered infeasible for CNN inference.
Direct-P is introduced for noncausal inference and a causal path that passes the forward quantization directly into backward into forward quantization is addressed, accelerating a complete single-GPU 8-billion-parameter update by up to 1.14$\times$.
Deep neural networks (DNNs) achieve high accuracy in image classification tasks. However, their high computational and hardware demands make them difficult to deploy on resourceconstrained edge devices. To address this challenge, this work proposes a Stochastic SqueezeNet architecture that integrates hybrid multiply-ac...
Mahanta Talakal, Mallikarjun Yeshlur, Omkar N. R. et al.· International Symposium on V...· 0 citations
To deploy deep neural networks on edge hardware, highly efficient inference schemes are necessary that retain high accuracy. This work presents W16A16, a high precision (16-bit), fast speed, low energy quantization method. On a widely applied microcontroller architecture Armv7E-M, our proposed approach achieves faster...
A PyTorch-based, research-oriented framework is introduced that incorporates freezing and pruning mechanisms for designing and optimizing binarized neural networks and a novel pruning method that accounts for the relative importance of learned parameters across abstraction levels is proposed.
This paper presents the design, simulation, and ASIC-focused implementation of a Binary Convolutional Neural Network (BCNN) tailored for energy-efficient edge AI applications. The proposed architecture utilizes binarized weights and activations, substituting standard multipliers with XNOR-popcount operations to reduce...
Aryan Kodan, R. S· International Conference Inn...· 0 citations
A memory-efficient hardware accelerator for depthwise separable convolution that minimizes off-chip memory traffic and parameter storage and performs the depthwise separable convolution with a small number of logic resources and on-chip memory, confirming its feasibility for resource-constrained edge devices.
Jaeseong Kim, Taehong Min, Chaebin Lee et al.· Electronics· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 14, 2026
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
Microsoft Research Blog· microsoft.comOct 12, 2026
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
