Scribd
Upload
238 views7 pages

TinyML: AI for Low-Power Devices

TinyML focuses on deploying compressed and optimized machine learning models on low-power devices like microcontrollers to overcome issues with running AI algorithms on dedicated hardware and in the cloud. It introduces AI into the edge computing layer by putting data storage and computation closer to the data source on tiny devices to offer low latency, low power consumption, and low bandwidth usage.

Uploaded by

Harsh Deshwal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
238 views7 pages

TinyML: AI for Low-Power Devices

TinyML focuses on deploying compressed and optimized machine learning models on low-power devices like microcontrollers to overcome issues with running AI algorithms on dedicated hardware and in the cloud. It introduces AI into the edge computing layer by putting data storage and computation closer to the data source on tiny devices to offer low latency, low power consumption, and low bandwidth usage.

Uploaded by

Harsh Deshwal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

TinyML : An Emerging Field

in AI
Introduction

What is TinyML?

TinyML focuses on deploying


compressed and optimized
machine learning models on
tiny, low-power devices such as
battery-powered
microcontrollers,and embedded
systems
Why TinyML?

It overcomes the side effects of AI

Cost Of Setting Dedicated Hardwares are


required to run AI algorithms is increasing

Cloud alternatives also doesn't seem to


overcome this issue because cloud compute
time is proportional to no of processes being
executed. This impacts the environment as
non-renewable energy is supplied to these
processing hardware.
Cloud , Fog and Edge Computing

In IOT Devices,

Cloud computing in the top layer is intended for highlevel data processing and storage.
However, the distance between cloud servers and the data source causes challenges
such as sluggish decision-making and latency.

Fog Computing introduced to overcome the increasing number of IoT devices,as a


decentralized computer layer between the cloud and the sensing components.This layer
performs data collection, medium processing, and decision making,decreasing the
quantity of information coming to the cloud layer.

The Lowest Layer is edge computing, which puts data storage and computation closer to
the source of the data.
TinyML introduces AI in this layer.
TinyML Advantages

As TinyML uses tiny device for the execution such


as microcontroller it offers low-latency,consumes
less power(few milliwats or microwatts), and uses
low bandwidth.

You might also like