Wepropose MCUNet, aframeworkthat jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference onmicrocontrollers.

Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones. We propose MCUNet, a framework that jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference on microcontrollers. TinyNAS adopts a two-stage neural architecture search approach that first optimizes the search space to fit the resource constraints, then specializes the network architecture in the optimized search space. TinyNAS can automatically handle diverse constraints (i.e.

TinyNAS is co-designed with TinyEngine, a memory-efficient inference library to expand the search space and fit a larger model.

The co-designing mechanism is the core contribution of the paper but the detailed process is not described clearly. It is suggested to provide an elaborate diagram or pseudocode to introduce the whole framework. It is meaningful to explore its generalization ability. Please demonstrate the potential/ability of MCUNet being deployed on more scenarios and tasks, e.g., more devices or tasks like object detection, semantic segmentation. But the experiments failed to highlight the improvements of the co-design scheme, when compared to those single design schemes. But it is unclear whether the overall network topology indeed is the main reason for the huge improvements.

All four knowledgeable referees support acceptance for the contributions, notably co-designing TinyNAS and TinyEngine for deep learning on IoT devices and promising experimental results on ImageNet, and I also recommend acceptance. Please make it sure to appropriately reflect what has been promised through rebuttal such as elaboration on co-design.

Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones. We propose MCUNet, a framework that jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference on microcontrollers. TinyNAS adopts a two-stage neural architecture search approach that first optimizes the search space to fit the resource constraints, then specializes the network architecture in the optimized search space. TinyNAS can automatically handle diverse constraints (i.e. TinyNAS is co-designed with TinyEngine, a memory-efficient inference library to expand the search space and fit a larger model.

This is the official implementation of TinyEngine, a memory-efficient and high-performance neural network library for Microcontrollers. TinyEngine is a part of MCUNet, which also consists of TinyNAS. MCUNet is a system-algorithm co-design framework for tiny deep learning on microcontrollers. TinyEngine and TinyNAS are co-designed to fit the tight memory budgets. We will soon release Tiny Training Engine used in MCUNetV3: On-Device Training Under 256KB Memory. If you are interested in getting updates, please sign up here to get notified!

Artificial intelligence (AI) is disrupting a multitude of industries. This article is a response to an article arguing that an AI Winter maybe inevitable. However, I believe that there are fundamental differences between what happened in the 1970s (the fist AI winter) and late 1980s (the second AI winter with the fall of Expert Systems) with the arrival and growth of the internet, smart mobiles and social media resulting in the volume and velocity of data being generated constantly increasing and requiring Machine Learning and Deep Learning to make sense of the Big Data that we generate. For those wishing to see a details about what AI is then I suggest reading an Intro to AI, and for the purposes of this article I will assume Machine Learning and Deep Learning to be a subset of Artificial Intelligence (AI). AI deals with the area of developing computing systems that are capable of performing tasks that humans are very good at, for example recognising objects, recognising and making sense of speech, and decision making in a constrained environment.

This branch of artificial intelligence curates your social media and serves your Google search results. Soon, deep learning could also check your vitals or set your thermostat. MIT researchers have developed a system that could bring deep learning neural networks to new--and much smaller--places, like the tiny computer chips in wearable medical devices, household appliances, and the 250 billion other objects that constitute the "internet of things" (IoT). The system, called MCUNet, designs compact neural networks that deliver unprecedented speed and accuracy for deep learning on IoT devices, despite limited memory and processing power. The technology could facilitate the expansion of the IoT universe while saving energy and improving data security.

This branch of artificial intelligence curates your social media and serves your Google search results. Soon, deep learning could also check your vitals or set your thermostat. MIT researchers have developed a system that could bring deep learning neural networks to new – and much smaller – places, like the tiny computer chips in wearable medical devices, household appliances, and the 250 billion other objects that constitute the "internet of things" (IoT). The system, called MCUNet, designs compact neural networks that deliver unprecedented speed and accuracy for deep learning on IoT devices, despite limited memory and processing power. The technology could facilitate the expansion of the IoT universe while saving energy and improving data security.