ℹ️ This semester also includes an Open Elective, Industrial Training / Seminar and SODECA as per RTU's teaching scheme. See the official PDF for the complete scheme.
Introduction: Objective, scope and outcome of the course.
1 hr
Unit 2
Deep Networks Basics: Learning algorithms, Maximum likelihood estimation, Building machine learning algorithm, Neural Networks Multilayer Perceptron, Back-propagation algorithm and its variants Stochastic gradient decent, Curse of Dimensionality, Deep feed forward networks.
8 hrs
Unit 3
Deep Learning Architectures: Machine Learning and Deep learning, Representation Learning, Width and Depth of Neural Networks, Activation Functions: RELU,LRELU,ERELU, Unsupervised Training of Neural Networks, Restricted Boltzmann Machines, Auto Encoders, Deep Learning Applications.
Sequence Modelling -Recurrent And Recursive Nets: Recurrent Neural Networks, Bidirectional RNNs, Encoder –decoder sequence to sequence architectures – BPTT for training RNN, Long Short Term Memory Networks. Computer Vision - Speech Recognition - Natural language Processing, Case studies in classification, Regression and deep networks.
9 hrs
Unit 6
Auto Encoders: Under complete Auto encoder, Regularized Auto encoder, stochastic Encoders and Decoders, Contractive Encoders.
Build a deep neural network model start with linear regression using a) Single variable b) Multiple variables
Write a program to convert : a) Speech into text b) Text into speech c) Video into frames
Build a feed forward neural network for prediction of logic gates.
Write a program for character recognition using: a) CNN b) RNN
Write a program to predict a caption for a sample image using : a) LSTM b) CNN
Write a program to develop : a) Auto encoders using MNIST Handwritten Digits. b) GAN for Generating MNIST Handwritten Digits. REFERENCE BOOKS 1 Navin Kumar Manaswi,Deep Learning with Applications Using Python Chatbots and Face, Object, and Speech Recognition With TensorFlow and Keras, Apress,2018. 2 Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2016. 3 Josh Patterson and Adam Gibson, “Deep learning: A practitioner's approach”, O'Reilly Media, First Edition, 2017 IV Year- VII & VIII Semester: B. Tech. (Artificial Intelligence and Data Science)
Object Detection and Tracking Robot: Create a robot with a camera that can detect and track objects in its field of view. Implement object detection algorithms and use them for tracking and interaction.
Autonomous Maze Solving Robot: Construct a robot that can autonomously navigate through a maze from the start to the finish. Implement maze -solving algorithms like A* or Dijkstra's algorithm.
Reinforcement Learning for Robotic Arm Control: Train a robotic arm to perform tasks using reinforcement learning. Implement algorithms like Deep Q -Networks (DQN) or Proximal Policy Optimization (PPO) to optimize arm movements.
Human-Robot Interaction using Natural Language Processing (NLP): Design a robot that can understand and respond to voice commands. Use NLP techniques to process and interpret human language to control the robot's actions.
Robot-Assisted Healthcare and Patient Interaction: Design a robot that can assist patients and healthcare professionals. Use AI to understand pati ent needs, provide information, and interact in a helpful and empathetic manner.
Gesture Recognition and Control of Robotic Arm: Build a robotic arm that responds to hand gestures. Train a machine learning model to recognize gestures, and use them to control the movements of the robotic arm.
Obstacle Avoidance Robot with Ultrasonic Sensors: Develop a robot capable of navigating an environment while avoiding obstacles using ultrasonic sensors. Implement basic obstacle avoidance algorithms and refine the robot's movements. REFERENCE BOOKS 1 Sebastian Thrun, Wolfram Burgard, and Dieter Fox, Probabilistic Robotics,MIT press 2 Francesco Amigoni and Matteo Matteucci, Artificial Intelligence for R obotics, Springer 3 Cameron Hughes and Tracey Hughes, Robot Programming: A Guide to Controlling Autonomous Robots, QUE Publishing
Advertisement
About the RTU 8th Sem AI & DS syllabus
This page shows the official Rajasthan Technical University (RTU), Kota syllabus for B.Tech 8th semester Artificial Intelligence & Data Science (AI&DS), taken directly from RTU's published PDF: every subject with its code, credits, marks and unit-wise topics. Use it to plan your preparation unit by unit, then practise with the RTU 8th Sem previous year papers and notes.
Frequently asked questions
What subjects are in the RTU 8th Sem AI & DS syllabus?
The theory subjects are Deep Learning and Its Applications (8AID4-01). Labs: Deep Learning and Its Application Lab, Robot Programming Lab.
Where can I download the official RTU 8th Sem AI & DS syllabus PDF?
Use the "Download official PDF" button on this page. It is the syllabus document published by Rajasthan Technical University (RTU), Kota.
Which session is this syllabus for?
The official document says it is effective from session 2020-21 for students admitted in 2020-21 onwards. RTU revises syllabi from time to time, so also check rtu.ac.in for notices.