Microcontroller for AI

 

It Depends on the program you want to make. If complex AI algorithms are needed then we might need to use powerful chips with more memory and processing power. But simple AI will need less processing power so low end chips will also work. let's we move into know about which microcontrollers are used for Ai

Why use Microcontrollers for Machine Learning and AI?

   

Low Energy Consumption

• Due to its small size,  processing power, memory and storage, microcontrollers consume very little energy and are efficient also it acquires a low amount of space.
• Normally, a lot of power is required to power GPU and computers for machine learning which causes limitations and constraints.
• However, microcontrollers are normally not wired into main power and rely on batteries or energy consumption. For example, a microcontroller can run on a single coin battery from weeks to even months that depends on its power harvesting.
• This makes microcontrollers easy to install and implement as it does not require to be plugged into the main power.

Cost

• Normally, for machine learning, you have to spend a few thousands to build a high performance machine learning workstation.
• However, with microcontrollers, you can easily implement in a few amount of cost which are also reliable.

Flexibility

• Microcontrollers are very common. They are basically everywhere around us like our household appliances, toys, cars, etc. The possibilities are endless when we bring machine learning to microcontrollers
• With microcontrollers, you can add AI to various devices without relying on network connectivity which are normally restrained by bandwidth, power and high latency.

Privacy

• Normally for machine learning, you will have to string all your raw data to the cloud which could contain confidential or private information.
• For microcontrollers, users do not have to worry about this problem because no data will have to leave the device.

Recommended Microcontrollers for Machine Learning

 

   You can make Bussiness queries by using the business queries section. You can find that at the bottom of this page

• You can make queries related to place ads, product placement, and advertising
• make project queries related to DIY project section (college and school students for their projects) 

 

Coral Dev Board

         

           

• The Coral Dev Board is a single-board computer with a removable system-on-module (SOM) that contains eMMC, SOC, wireless radios, and Google’s Edge TPU. It’s perfect for IoT devices and other embedded systems that demand fast on-device ML inferencing.
• This module, known as a System On Module (SOM) sits on top of a connecting baseboard and contains everything that makes the board tick. The CPU, GPU, RAM, Wi-Fi chip and flash memory are all present in one removable unit which can be quickly swapped out.

• CPU: NXP i.MX 8M SOC (quad Cortex-A53, Cortex-M4F)
• GPU: Integrated GC7000 Lite Graphics
• Coprocessor: Google Edge TPU
• RAM: 1GB LPDDR4
• Flash memory: 8GB eMMC
• Connectivity: Wi-Fi 2x2 MIMO (802.11b/g/n/ac 2.4/5GHz) Bluetooth 4.1
• Dimensions: 48 x 40 x 5mm

The baseboard has its own set of specifications:

• Flash memory: MicroSD
• USB: Type-C OTG Type-C power Type-A 3.0 host Micro-B serial console
• LAN: Gigabit Ethernet port
• Audio: 3.5mm audio jack (CTIA compliant) Digital PDM microphone (x2) 2.54mm 4-pin terminal for stereo speakers
• Video: HDMI 2.0a (full size) 39-pin FFC connector for MIPI-DSI display (4-lane) 24-pin FFC connector for MIPI-CSI2 camera (4-lane)
• GPIO: 3.3V power rail 40 - 255 ohms programmable impedance ~82 mA max current
• Power: 5V DC (USB Type-C)
• Dimensions: 88 x 60 x 24mm

Python is the only currently supported programming language. C++ support is coming soon

• Pros:
  • As the Coral DevBoard has the newest chip the
    NXP i.MX 8M SOC (Quad-core Cortex-A53, plus Cortex-M4F), it is also the most efficient out of all the microcontrollers.
  • Supports Wifi and Bluetooth.
  • On board TPU is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt).
  • Has video processing units and a Vivante GC700 lite GPU which can be used for traditional image and video processing. It also has a Cortex-M4F low power micro-controller which can be used to talk to other sensors like temperature sensor, ambient light sensor etc.
• Cons:
• Only compatible and you can only use TensorFlow Lite as your deep learning framework, inflexible and unable to use any other software.
• It is expensive than other boards.

NVIDIA® Jetson Nano™ Developer Kit

     

• The NVIDIA® Jetson Nano™ Developer Kit delivers computing performance to run modern AI workloads at unprecedented size, power, and cost. Developers, learners, and makers can now run AI frameworks and models for applications like image classification, object detection, segmentation, and speech processing.

• GPU: 128-core Maxwell™ GPU
  
• CPU: quad-core ARM® Cortex®-A57 CPU
  
• Memory: 4GB 64-bit LPDDR4
• Storage: Micro SD card slot (requires an external minimum 16G TF card)
• Video:
  • Encode: 4K @ 30 (H.264/H.265)
  • Decode: 4K @ 60 (H.264/H.265)
• Interfaces:
  • Ethernet: 10/100/1000BASE-T auto-negotiation
  • Camera: 12-ch (3x4 OR 4x2) MIPI CSI-2 DPHY 1.1 (1.5Gbps)
  • Display: HDMI 2.0, DP (DisplayPort)
  • USB: 4x USB 3.0, USB 2.0 (Micro USB)
  • Others: GPIO, I2C, I2S, SPI, UART
• Power:
  • Micro USB (5V 2A)
  • DC jack (5V 4A)
• Dimensions:
• Core module: 69.6 mm × 45 mm
• Whole kit: 100mm × 80mm × 29mm

Jetson Nano is also supported by NVIDIA JetPack, which includes a board support package (BSP), CUDA, cuDNN, and TensorRT software libraries for deep learning, computer vision, GPU computing, multimedia processing, and much more. The SDK also includes the ability to natively install popular open source Machine Learning (ML) frameworks such as TensorFlow, PyTorch, Caffe / Caffe2, Keras, and MXNet, enables the developers to integrate their favorite AI model / AI framework into products fast and easily.

     

  

• Pros:
  • Better and more support for deep learning frameworks like
    Tensorflow, PyTorch, Caffe/Caffe2, Keras, MXNet, and many more.
  • Good Library support.
  • Has Video Encoder and decoder unit and also supports NVidia TensorRT accelerator library for FP16 inference and INT8 inference.
  • Floating-point GPU acceleration.
• Cons:
  • Weaker core than Coral Dev Board, however, it offers decent performance but not as efficient.
  • Requires an additional external wifi dongle for Wifi.

Check out  my previous tutorial that How to make wifi hacker

Sipeed MAIX GO Suit (MAIX GO + 2.8 inch LCD + ov2640 with M12 lens)

• MAIX is Sipeed’s purpose-built module designed to run AI at the edge. It delivers high performance in a small physical and power footprint, enabling the deployment of high-accuracy AI at the edge, and the competitive price make it possible embed to any IoT devices.

Core Speed	RISC-V Dual Core 64bit, 400Mhz adjustable
GPU	KPU (Neural Network Processor) inside, 64 KPU which is 576bit width and APU (Audio Processor), support 8mics, up to 192KHz sample rate.
RAM	8MB high-speed SRAM,400MHz frequency(able to reach 800MHz)
Software Compatibility	Supports Tiny-Yolo, Mobile Net-v1, Tensorflow, FreeRTOS and MicroPython
Additional features	-Breadboard friendly board, and micropython available. -Open source. -On board JTAG&UART based on STM32F103C8, debug M1 without extra Jlink. -Has lithium battery manager chip with power path management function allowing you to use the board with lithium battery and usb power without conflict.
	$40.90 for MAIX GO Suit which includes – Sipeed MAIX GO Dev Board. – 2.8 Inch LCD

• Pros:
  • It is probably the cheapest development board you can get out in the market currently. entire suit which comes with case, touch LCD, camera lens, wifi antenna, USB type-C cable, Li-ion battery with screw & studs.
  • Provides end-to-end hardware + software infrastructure for facilitating users AI-based solutions
  • At a size of 88x60mm, it is small which allow it to be embedded at the edge to any IoT device.
  • Able to run microphython on the board.
• Cons:
  • Documentation and Support is not as developed compared to the other development boards at this stage.
  • Libraries support is not as developed compared to the others.

Raspberry Pi 4 Computer Model B

   

• The Raspberry Pi 4 Model B is the latest product in the popular Raspberry Pi range of computers. It offers ground-breaking increases in processor speed, multimedia performance, memory, and connectivity while retaining backwards compatibility and similar power consumption as the prior generation Raspberry Pi 3 Model B+.

• Broadcom BCM2711, Quad core Cortex-A72 (ARM v8) 64-bit SoC @ 1.5GHz
• 2GB, 4GB or 8GB LPDDR4-3200 SDRAM (depending on model)
• 2.4 GHz and 5.0 GHz IEEE 802.11ac wireless, Bluetooth 5.0, BLE
• Gigabit Ethernet
• 2 USB 3.0 ports; 2 USB 2.0 ports.
• Raspberry Pi standard 40 pin GPIO header (fully backwards compatible with previous boards)
• 2 × micro-HDMI ports (up to 4kp60 supported)
• 2-lane MIPI DSI display port
• 2-lane MIPI CSI camera port
• 4-pole stereo audio and composite video port
• H.265 (4kp60 decode), H264 (1080p60 decode, 1080p30 encode)
• OpenGL ES 3.0 graphics
• Micro-SD card slot for loading operating system and data storage
• 5V DC via USB-C connector (minimum 3A*)
• 5V DC via GPIO header (minimum 3A*)
• Power over Ethernet (PoE) enabled (requires separate PoE HAT)
• Operating temperature: 0 – 50 degrees C ambient

• Pros:
  • Cheap option for an SBC starting at $35 for 1GB.
  • Good CPU processing power with its Broadcom BCM2711, quad-core Cortex-A72 (ARM v8) 64-bit SoC @ 1.5GHz.
  • Recommended for beginners as it has one of the biggest communities and support for debugging. It also has many detailed tutorials and projects for the Raspberry Pi 4. It also has good documentation.
• Cons: 
  • Weaker GPU compared to the other boards.
  • Requires additional heatsink and fan for sustained inference to prevent overheating.

Hope you have liked this post and  don't forget to share between those who aspire to learn new things