newb in ARM for Machine Learning

Log in or register to post comments
Go To Last Post
2 posts / 0 new
Author
Message
hamisu
hamisu's picture
Level: Hangaround
Joined: Fri. Jan 19, 2018
Posts: 235 View posts
#1
Posted by hamisu: Sat. Sep 5, 2020 - 04:54 AM
  • 1
  • 2
  • 3
  • 4
  • 5
Total votes: 0

 

I am newb here.  I wanted to pick up some knowledge toward embedded Machine Learning,

I have the Atmel ICE, all the while I used it only AVR. Does not use the SAM side of the ICE.  I have zero experience in ARM device. 

 

Can someone give me a direction whether I should pick up ARM devices or ESP32 ?

If ARM, what are the ARM demoboard i shud get for learning purpose. 

 

My goal is to learn up using embedded machine learning or AI for image processing and intelligent sensor data processing. 

Is microcontroller processing power sufficient for image processing without connecting to server ?

 

 

 

Tags:

Tools, Evaluation and Development Kits (ARM-related)
Top
Kartman
Kartman's picture
Level: 10k+ Postman
Joined: Thu. Dec 30, 2004
Posts: 24978 View posts
Location: Melbourne,Australia
Posted by Kartman: Sun. Sep 6, 2020 - 05:19 AM
  • 1
  • 2
  • 3
  • 4
  • 5
Total votes: 0

Your question is too broad. ARM encompasses devices from the very small to the very large. The actual cpu core is irrelevant sans the actual performance.

 

If you want to learn about machine learning, then the pc is the better solution methinks. There's a lot of theory to work through.

Whether the code runs on an embedded platform or other, the concepts are the same, the amount of memory and processing will certainly differ.

 

I bought a maix bit with the camera and lcd screen recently. The processor has an AI accelerator. There's some examples of video detection and processing. Nevertheless, you tend to develop the stuff on a PC then move it down to smaller devices.

Top