Scribd
Upload
4 views

Course Outlines PH.D Computing Intelligence

hi

Uploaded by

aturiharsha1
Copyright
© © All Rights Reserved
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
4 views

Course Outlines PH.D Computing Intelligence

hi

Uploaded by

aturiharsha1
Copyright
© © All Rights Reserved
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 3

Intelligent Systems

Course Title Intelligent systems Credits-3

Course Course
Core L-T-P-S-C 3-0-0-0-3
Code category
Approval
Version Learning Level
Details
This course provides a comprehensive introduction to Artificial Intelligence (AI), covering its
fundamental concepts, applications, and practical implementation. Students will explore various
Course Description machine learning algorithms, deep learning architectures, and the integration of AI with hardware
and software systems. The course will also delve into the role of AI in addressing sustainability
challenges.
Provide a comprehensive understanding of the fundamental concepts and techniques of Artificial
Intelligence (AI), machine learning, and deep learning.
Equip students with the practical skills to apply AI algorithms to solve real-world problems in
Course Objective various domains.
Delve into the synergy between AI and technology, examining its applications in VLSI design,
embedded systems, and wireless communication through Python programming. Additionally, explore
the pivotal role AI plays in advancing sustainability initiatives.
BT Level
CO1: Understand the fundamentals of AI and machine learning. (L2)
CO2: Apply AI techniques to real-world problems (L3)
Course Outcome CO3: Implement AI projects using Python (L5)
CO4: Develop AI-powered IoT & Embedded systems, VLSI Designs and (L4)
wireless communication use cases.
CO5: Leverage AI for sustainable solutions (L4)

CO, PO, and PSO Mapping

CO PO -1 PO-2 PO-3 PO-4 PO-5 PO-6 PO-7 PO-8 PSO-1 PSO-2 PSO-3
CO-1 3 1 1 1 2 1 1 2 3 1 1
CO-2 3 3 2 3 2 1 1 1 3 2 1
CO-3 3 3 3 2 3 3 1 1 3 3 3
CO-4 3 3 2 2 3 3 1 1 3 3 3
CO-5 3 3 3 2 3 3 1 1 3 3 3
1: Weakly related, 2: Moderately related, and 3: Strongly related

Outline Teaching Schedule

Unit Topics No. of Sessions


1 Module 1: Foundations of ML
Application areas of AI, AI Basics NN basics (Perceptron and MLP, FFN, back
propagation) Components of Learning process, Types of data, Classification of data.
Random Forest, Decision Trees, Support Vector Machines, KNN, Naïve Bayes,
10
Regression. Unsupervised and Reinforcement Learning Algorithms
Clustering-K-Means, K Nearest neighbours, Association Rule Learning,
Dimensionality Reduction-PCA, SVD
Reinforcement Learning: Markov Decision, Monte Carlo Prediction
Module-2 Introduction to Deep Learning
Introduction, Need for Deep Learning, Deep Learning Models-Restricted
2 06
Boltzmann Machines, Deep Belief Nets, Convolution Networks, Recurrent Nets
Additional Deep Learning Models- Auto encoders, Recursive Neural Tensor Nets.
Module 3: Introduction to Python Programming (Coursera)
3 13
Regression, classification, Linear classification, Clustering.
Module 4: Intelligent Hardware
 AI in VLSI Design:
o Overview of AI-driven design automation tools and techniques.
o Case studies of AI applications in VLSI design (e.g., layout
generation, circuit optimization).
 AI on Embedded Devices:
o Challenges and opportunities of running AI algorithms on embedded
4 08
systems.
o Techniques for optimizing AI models for low-power, resource-
constrained devices.
 AI for Wireless Networks:
o Intelligent resource allocation, network optimization, and interference
management.
o AI-driven predictive maintenance for wireless infrastructure.
Module 5: AI's Role in Sustainability: Use cases
5 Sustainable Manufacturing/Cities, Computer Vision, Autonomous Systems, Human- 08
Robot Interaction, Medical Diagnosis.

Total Sessions 45
Essential Readings:
Recommended 1.Tom M. Mitchell, “Machine Learning”, by McGraw Hill, 2017.
Resources: 2.Kumar, U Dinesh, “Machine Learning Using Python” Wiley India New
Delhi 2019.
Online: https://www.coursera.org/lecture/machine-learning-with-python/course-introduction-
ignHI

Assessment Method (Mapped with CO’s)

Sl. No. Detail Weightage CO

1 Online forum 10 CO 3- CO-4

2. Simulation Project 15 CO-4

3. Presentation 10 CO-3

4 MSE 10 CO-1- CO-3

4. Semester End Examination 50 CO-1- CO-5


If level BTL-4 and Above, Sample assessment questions to be given
1.Analyze the ethical implications of developing AI systems that can make autonomous decisions.
2. Discuss the trade-offs between completeness, optimality, and efficiency in search algorithms.
3. Analyze the challenges and potential solutions for representing and reasoning with uncertain information.
4. Evaluate the effectiveness of different evaluation metrics (e.g., accuracy, precision, recall, F1-score) for assessing the
performance of machine learning models.
5. Analyze the challenges and potential solutions for natural language understanding, including ambiguity, context, and
world knowledge.

You might also like