Scribd
Upload
21 views6 pages

Exp 1 ML Supervised Learning Using Edge Impulse

Uploaded by

Yachika Yadav
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
21 views6 pages

Exp 1 ML Supervised Learning Using Edge Impulse

Uploaded by

Yachika Yadav
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Machine Learning Laboratory

Experiment No 1
Aim: Implement Supervised Learning using Edge Impulse.

Practical Learning Objectives:

The objective of this practical is to

i. Understand supervised algorithm.


ii. Use Edge Impulse to implement supervised algorithm using smart devices.

Apparatus:

Sr. No. Instrument / Component


1 PC/Laptop
2 Mobile Phine

Theory:
Supervised Algorithm:

Supervised learning is an approach to creating artificial intelligence (AI), where a computer


algorithm is trained on input data that has been labeled for a particular output. The model is
trained until it can detect the underlying patterns and relationships between the input data and the
output labels, enabling it to yield accurate labeling results when presented with never-before-
seen data.

Supervised learning is good at classification and regression problems, such as determining what
category a news article belongs to or predicting the volume of sales for a given future date. In
supervised learning, the aim is to make sense of data within the context of a specific question.

How does supervised learning work?


Like all machine learning algorithms, supervised learning is based on training. During its
training phase, the system is fed with labeled data sets, which instruct the system what output is
related to each specific input value. The trained model is then presented with test data: This is
data that has been labeled, but the labels have not been revealed to the algorithm. The aim of the
testing data is to measure how accurately the algorithm will perform on unlabeled data.

Edge Impulse:

Edge Impulse is the leading development platform for embedded machine learning, used by over
1,000 enterprises across 10,000 ML projects worldwide. Edge Impulse is the leading
development platform for machine learning on edge devices, free for developers and trusted by
enterprises. Edge Impulse is designed to integrate beautifully with the tools that embedded
engineers use every day, providing a high-level interface for incorporating machine learning into
projects. Edge Impulse makes use of the TensorFlow ecosystem for training, optimizing, and
deploying deep learning models to embedded devices.

EDGE ML: Edge ML is a technique by which Smart Devices can process data locally (either
using local servers or at the device-level) using machine and deep learning algorithms. The term
edge refers to processing that occurs at the device- or local-level (and closest to the components
collecting the data) by deep- and machine-learning algorithms. Unlike traditional machines,
Edge ML devices will analyze and process incoming data at the source and determine what
needs to be processed by more powerful algorithms in the Cloud, versus what can be processed
locally.

Steps to implement supervised learning using Edge Impulse:

1. Open Edge Impulse Website and Sign up if new user.


2. Click on “ Click here to build your first ML model”
3. Acquire data “Lets collect some data”
4. Use Mobile Phone and connect it to Edge Impulse by scanning QR code.
5. You will get message that the device is connected.
6. Acquire Images by capturing through smart device i.e. mobile phone.
7. Click on “Collecting Images” on mobile phone and give access to camera and capture
images.
8. Label data while capturing images. For e.g. If cup images are captured then give label in
phone as “cup”. If arduino images are to be captured then give label as”arduino” in
phone. Give label once while collecting images of one category. Change the label when
images of other category are to be captured.
9. Observe images in Data Acquisition.
10. Click on” Create Impulse”.
11. Add a processing block and a learning block and save impulse.
12. Go to Image and save parameters and click on generate features.
13. Take Print screen of these features as first observation.
14. Observe the graph after generating features.
15. Go to “Transfer Learning” and start training.
16. Take screenshot when the training is complete.
17. You can retrain the model if any new data in input needs to be added otherwise skip this
step.
18. Go to “Model Testing”
19. Click on “Switch to Classification Mode” on Mobile. Give access to camera.
20. Capture test data and watch the inferences.
21. Take screen shots of your mobile output.
22. Go to Model Testing and say “Classify all”
23. Take printout of the screen displaying output.
24. If accuracy is not good then retrain the model by adding more inputs and reoeat above
procedure.

Result and discussion:


Conclusion:

After performing the practical, the learner can: Marked


√
i. Understand Supervised Algorithm. √
ii. Implement the algorithm in Edge Impulse. √
iii. Calculate the accuracy.
√

Outcome PLO 1 PLO 2 PLO 3 Performance Attendance Total Score E&TC DEPARTMENT- TCET

Date of
Weight 20 20 20 20 20 100 Performance: _________

Date of Correction:___________

Roll No:_________
Score
Marks: ______/100
Signature of Faculty:

You might also like