T01:- Introduction to Ondevice AI

                Understanding Of On-device Ai

Smart stuff like phones and cars are getting smarter . They can crunch data and learn without needing the internet all the time. Qualcomm is a big part of making this happens. 

                                     Fig - 1.1(On-device AI)

So, What is On-device AI?

On-device means smart devices like phones or smartwatches can work without need of constant internet

connection. Its like having a live brain inside your gadgets, making quick decisions and performing task

without the need of live servers. This technology is good for things like voice assistants and image recognition , as it reduces the latency and ensures privacy by keeping data local.

                                          Fig- 1.2 ( ON- device benefits)

Benefits of choosing On-device Ai over Cloud

1. First and foremost thing , it gives us privacy by keeping sensitive data locally on the device.

2. Secondly it improves response time since computations are performed locally , reducing latency 

    and ensuring faster interaction.

3. Additionally , On-device AI enables functionality even in areas with limited or no internet connection

So, Qualcomm has provided us the two technologies that can bring this feature  On-device AI into our daily life.

1. Qualcomm Neural processing SDK.

2. Ai direct engine SDK.

Now we will begin to understand the basic overview of Qualcomm Neural Processing SDK.

It is a set of tools and resources given by the Qualcomm Technologies to implement and run efficiently 

machine learning model which is given in the SDK. It has libraries , APIs  and tools to help developers

to fully utilize the neural processing capabilities of snapdragon-processors for task recognition like image recognition, natural language processing and etc. This SDK enables us to fully utilize the power of On-device AI. Basically Snapdragon processors are capable of running the Ai powered applications 

on Mobile devices , IOT devices and other edge devices.

                             Fig 1.3(Qualcomm Neural processing SDK WORKFLOW)

-> It allows us(developers) to convert the already pre-defined neural network into the DLC(Deep Learning Container ) , if DLC is not familiar we will explain this into later part of the blog.

-> Now we have the basic understanding of Qualcomm neural Processing SDK, later we will explain how we can actually run machine learning model using this Qualcomm neural processing SDK.

    

Now , we will try to understand the basic overview of the Ai direct engine SDK.

We can also called this Qualcomm Neural Network(QNN) . It is a toolkit that is given by the Qualcomm that helps developers to work more closely with specific hardware in the Snapdragon 

processors. It will make AI model run more smoothly on the device. It will basically enhance the 

performance which is done by Neural processing SDK.

It gives access to the different parts of the hardware that are good at handling at AI tasks. 

                                         Fig-1.4 (Qualcomm AI engine Direct SDK) 

-> So, in this blog our learning stays here , from the next blog we will first setup the Qualcomm neural 

   Processing SDK into our System. It will be a process of how we can actually run machine learning model into ON-device and understand the whole scenarios behind the Qualcomm Neural Processing SDK(SNPE).

For more understanding you can also refer this website