DEEPLEARNING and Robotics LABORATORY

[ Revised Credit System ]

(Effective from the academic year 2022 onwards)

SEMESTER - VI
Subject Code IA Marks 60

Number of Practical Hours/Week 02 Exam Marks 40

Total Number of Practical Hours 36 Exam Hours 02

CREDITS - 01

Course objectives:

This laboratory course enables students to

 Understand and implement various neuron models using different activation functions and
analyse their impact on learning.
 Explore and apply different neural network learning algorithms such as error correction,
Hebbian learning, and competitive learning to train networks.
 Implement and analyse perceptron-based models for logic gate operations, including XOR
using multi-layer perceptrons and Radial Basis Function (RBF) networks.
 Train and evaluate self-organizing maps (SOMs) and recurrent networks using competitive
learning and backpropagation.
 Integrate neural networks with robotic applications for motion control, object detection,
and automated sorting using machine vision techniques.

Implement the different learning algorithms of an artificial neural network with robotics

a Implement the basic neuron and update the learning parameter using different
1 activation functions. Show the graph.
b Implement the neuron using error correction learning algorithm and memory-based
learning algorithm.
2 Implement the neuron using Hebbian Learning algorithm and show the graph to
differentiate the hypothesis between Hebb and Co-variance learning.
a Implement the Gate Operations using Single Layer Perceptron.
3 b Implement the XOR gate operations using multi-layer perception and show the
error propagation by iterating the learning rate.
 4 Implement the single linear neuron model with a Hebbian adaptation to describe the
principal component of the arbitrary input distribution
5 a. Implement the features used in Self organizing maps using competitive learning
algorithm.
b. Implement the back propagation algorithm for training a recurrent network using
temporal operation as a parameter into a layer feed forward network.
6 Implement the Hop-field network using associative memory method
7 Design a neural network system by taking a suitable data set and demonstrate training,
testing and performance of the systems.
8 Write a Python program to move a robotic arm through three waypoints with different
speeds. The robot should pause for 2 seconds at each waypoint before proceeding.
9 Implement a Python program to control a robotic gripper for picking up and placing an
object at a new location.
10 Write a Python program for an automated pick-and-place operation using a sensor to
detect objects. The robot should check for an object before picking it up and placing it in
a storage bin.
11 Detect objects using color filtering and shape detection in OpenCV, then print the
object’s position. This can be integrated with a robotic arm for sorting tasks.
Sort objects based on color detection and move them to different locations using a
12 robotic arm.

Course outcomes:

At the end of this course, students will gain the

1. Develop and implement neural networks with various activation functions and learning
algorithms for classification and prediction tasks.
2. Compare and evaluate different learning methods, such as Hebbian, memory-based,
and backpropagation algorithms, for neural network training.
3. Implement deep learning-based robotic applications, including motion planning,
object detection, and sorting using Python and machine vision.
4. Analyse and optimize neural network models by adjusting learning rates,
regularization parameters, and network architectures to improve performance.

Conduction of Practical Examination:

1. All laboratory experiments (TWELVE nos) are to be included for practical examination.
2. Strictly follow the instructions as printed on the cover page of answer script
3. Marks distribution: Procedure + Conduction:15+25 (40)
4. Change of experiment is not allowed.
References:

1. Leonardo De Marchi and Laura Mitchell, Hands-On Neural Networks: Learn how to
build and train your first neural network model using Python, 1st ed, Packt Publishing,
2019.
2. Michael Taylor, A Neural network: A Visual Introduction for Beginners, Blue Windmill
Media, 2017.
3. Simon Haykin, Neural Networks and Learning Machines, 3rd ed, Pearson, Prentice Hall,
2009.
4. Jeff Heaton, Introduction to Neural Networks with Java, 2nd ed, Heaton Research, Inc.,
2008.
5. Hughes Cameron, “Robot Programming”, Pearson Publishers, 2016
6. J. Srinivas, “Robotics: Control and Programming”, Narosa Publication, 2009
7. Lentin Joseph, “Learning Robotics Using Python”, Second Edition Design, simulate, program,
and prototype an autonomous mobile robot using ROS, OpenCV, PCL, and Python, Packt
Publishing Paperback – 1 January 2018.
8. Staple Danny, “Learn Robotics Programming”, Packt Publishing Limited, Feb 2021 3.
9. Kailashi Chandra Mahajan, Prashant Kumar Patnaik, Raghvendra Kumar, “Robotics for
Engineers”, Vikas Publishing House , 2016