DEPARTMENT

OF

COMPUTER SCIENCE AND ENGINEERING

(ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING)

COURSE FILE
DEEP LEARNING

B. TECH IV YEAR I SEMESTER – R22 (REGULATION)

 Course Data Sheet
Faculty Details

Name of the Faculty : Mr. KONATALA LOKESH

Designations : Assistant Professor

Department : Computer Science and Engineering (AIML)

Course Details

Name of the Programme : B. Tech Batch : 2022-2026

Branch : CSM Year/ Sem : IV /I

Course Code : Course name : DEEP LEARNING

Regulation : R22 LTPC :3003

Course category : Regular No. of students: 67+ 67+63

Prerequisite : knowledge on machine learning and probability& Statistics

Assessment Methods : Mid I & II Test, Assignment (A), PPT & Semester End
Examination (SEE)

Course Coordinator : Mr. K. Lokesh

Signature with date

Course Faculty Course Coordinator Programme HoD

Coordinator

COURSE FILE CONTENT

1. Institute Vision & Mission, Department Vision & Mission

2. Blooms Taxonomy Level
3. POs, PSOs & PEOs Statements
4. Course information

4.1 Course Information Sheet (CIS) with syllabus

4.2 Nominal Rolls

4.3 COs to POs & PSOs mapping matrix

4.4 Class time table and Individual Time Table

4.5 Teaching Plan

4.6 Academic Calendar

5. Lecture Notes

5.1 Unit Wise Lecture Notes (HWN)

5.2 Add on Course Material/ Content Beyond the Syllabus

6. Question Bank
6.1 Unit Wise Question Bank
6.2 University Question Papers/ Previous Year QP

7. Continuous Evaluation

7.1 Mid-1 and Mid-2 Question Papers with key (BTL)

7.2 Assignment questions with Keys (BTL)

7.3 Sample Mid-1 and Mid-2 Answer Sheets

7.4 Sample Assignments Sheets

7.5 Sample PPT/ Presentation Hard copy

7.6 Internal mark sheet – Final

8. Attendance Register (Daily Attendance &Topic Delivery Report)

9. CD/DVD (All Course Information-like NPTEL, E-lectures, Unit wise PPT Slides
etc.,.

INSTITUTION VISION
 To emerge as a Center of Excellence for producing professionals who shall be the
leaders in technology innovation, entrepreneurship, management and in turn contribute for
advancement of society and human kind.

MISSION
 To provide an environment of learning in emerging technologies.
 To nurture a state of art teaching learning process and R&D culture.
 To foster networking with Alumni, Industry, Institutes of repute and other stakeholders
for effective interaction.
 To practice and promote high standards of ethical values through societal commitment.

DEPARTMENT VISION
VISION OF THE DEPARTMENT

 To teach excellence education for undergraduates in the field of Artificial Intelligence

and Machine Learning in the technological-embedded domain and make professionals
who help the better cause of society.

&
MISSION
MISSION OF THE DEPARTMENT

 Impart demanding training to create knowledge through the state-of-the-art ideas and
skills in Artificial Intelligence and Machine Learning.
 Facilitate the students to adapt to the rapidly changing technologies by providing
cutting-edge laboratories and facilities.
 Kick off the research and training, paying special attention to the essential skills of the
subsequent generation's workforce.

2. Blooms Taxonomy Level

POs, PSOs & PEOs Statements

Program Educational Objectives (PEOs):

PEO 1: To provide students with a foundation in the principles of computer science, including
mathematics and basic engineering necessary to find answers to the technological issues of
modern society.
PEO 2: To provide students a breadth of knowledge in computer science and related
engineering disciplines in order to enable them to understand engineering trade-offs across
multiple disciplines, work effectively as an individual and as a member in multidisciplinary
teams, and have successful careers in a broad range of field
PEO 3: To provide awareness of security and laws pertaining to cyber usage, ethical issues
related to computing and to provide knowledge on subject protection through Intellectual
Property Rights.
PEO 4: To provide students with specialized knowledge in focused areas of their choice, in
order to strengthen them to make contributions to a specific discipline and pursue post
graduation or research
PEO 5: To train students in problem solving skills in design, development and analysis for
interpretation and synthesis of data and create awareness for lifelong learning.
Program Outcomes (POs):
PO1: Engineering and Knowledge: Apply knowledge of mathematics, science, engineering
fundamentals and an engineering specialization to the solution of complex engineering
problems.

PO2: Problem Analysis: Identify, formulate, review research literature, and analyze complex
engineering problems reaching substantiated conclusions using first principles of mathematics,
natural sciences, and engineering sciences.
PO3: Design/Development of Solutions: Design solutions for complex engineering problems
and design system components or processes that meet the specified needs with appropriate
consideration for the public health and safety, and the cultural, societal, and environmental
considerations.
PO4– Conduct investigations of complex problems: Use research-based knowledge and
research methods including design of experiments, analysis and interpretation of data, and
synthesis of the information to provide valid conclusions.
PO5– Modern tool usage: Create, select, and apply appropriate techniques, resources, and
modern engineering and IT tools including prediction and modeling to complex engineering
activities with an understanding of the limitations.
PO6– The engineer and society: Apply reasoning informed by the contextual knowledge to
assess societal, health, safety, legal and cultural issues and the consequent responsibilities
relevant to the professional engineering practice.
PO7– Ethics: Apply ethical principles and commit to professional ethics and responsibilities
and norms of the engineering practice.
PO8– Individual and team work: Function effectively as an individual, and as a member or
leader in diverse teams, and in multidisciplinary settings.
PO9– Communication: Communicate effectively on complex engineering activities with the
engineering community and with society at large, such as, being able to comprehend and write
effective reports and design documentation, make effective presentations, and give and receive
clear instructions.
PO1– Project management and finance: Demonstrate knowledge and understanding of the
engineering and management principles and apply these to one’s own work, as a member and
leader in a team, to manage projects and in multidisciplinary environments.
PO11– Life-long learning: Recognize the need for, and have the preparation and ability to
engage
Program Educational Objectives (PEOs)
PEO1 – Graduates will obtain robust knowledge in the field of artificial intelligence and
machine learning theory and principles for classifying, examining and solving problems.
PEO2 – Graduates will upgrade skill to work efficiently within a squad and apply suitable
practices within a skilled and ethical framework for societal needs.
PEO3 – Graduates will pursue higher education and accomplish sustainable growth through
lifelong learning and research.
Program Specific Outcomes (PSOs)
PSO1 - An ability to apply unconventional fundamental AI technologies, to citation
information and deliver knowledge to intelligent decision-making systems.
PSO2 - An ability to grow an ethical and contemplative approach to the machine learning tools
that can address complex reasoning tasks for the enhancement of society.

Course information

4.1 Course Information Sheet (CIS) with syllabus

4.2 Nominal Rolls

4.3 COs to POs & PSOs mapping matrix

4.4 Class time table and Individual Time Table

4.5 Teaching Plan

4.6 Academic Calendar

 4.1 Course Information Sheet (CIS) with syllabus

PROGRAMME:
DEGREE: [Link]
COMPUTER SCIENCE AND ENGINEERING(AIML)

COURSE: DEEP LEARNING SEMESTER: IV/ I L T P C: 3 0 0 3

COURSE CODE: AM701PC

COURSE TYPE: CORE
REGULATION: R22

COURSE AREA/DOMAIN: DEEP LEARNING CONTACT HOURS: 4+1 (Tutorial) hours/Week.

CORRESPONDING LAB COURSE CODE (IF ANY):

SYLLABUS:
UNIT DETAILS HOURS
Machine Learning Basics
Learning Algorithms, Capacity, Overfitting and Underfitting, Hyperparameters and Validation Sets,
Estimators, Bias and Variance, Maximum Likelihood Estimation, Bayesian Statistics, Supervised
I Learning Algorithms, Unsupervised Learning Algorithms, Stochastic Gradient Descent, Building a 10
Machine Learning Algorithm, Challenges Motivating Deep Learning
Deep Feedforward Networks Learning XOR, Gradient-Based Learning, Hidden Units, Architecture
Design, Back-Propagation and Other Differentiation Algorithms

II Regularization for Deep Learning 11

Parameter Norm Penalties, Norm Penalties as Constrained Optimization, Regularization
and Under-Constrained Problems, Dataset Augmentation, Noise Robustness, Semi-
Supervised Learning, Multi- Task Learning, Early Stopping, Parameter Tying and
Parameter Sharing, Sparse Representations, Bagging and Other Ensemble Methods,
Dropout, Adversarial Training, Tangent Distance, Tangent Prop, and Manifold Tangent
 Classifier, Optimization for Training Deep Models, Learning vs Pure Optimization,
Challenges in Neural Network Optimization, Basic Algorithms, Parameter Initialization
Strategies, Algorithms with Adaptive Learning Rates
Convolutional Networks
The Convolution Operation, Motivation, Pooling, Convolution and Pooling as an Infinitely
III Strong Prior, Variants of the Basic Convolution Function, Structured Outputs, Data Types, 10
Efficient Convolution Algorithms, Random or Unsupervised Features

Recurrent and Recursive Nets

Unfolding Computational Graphs, Recurrent Neural Networks, Bidirectional RNNs,
Encoder-Decoder Sequence-to-Sequence Architectures, Deep Recurrent Networks,
IV Recursive Neural Networks, The Challenge of Long-Term Dependencies, Echo State 10
Networks, Leaky Units and Other Strategies for Multiple Time Scales, The Long Short-
Term Memory and Other Gated RNNs, Optimization for Long- Term Dependencies,
Explicit Memory
Practical Methodology: Performance Metrics, Default Baseline Models, Determining Whether to
Gather More Data, Selecting Hyperparameters, Debugging Strategies, Example: Multi-Digit Number
V Recognition 11
Applications: Large-Scale Deep Learning, Computer Vision, Speech Recognition, Natural Language
Processing, Other Applications.
TOTAL HOURS 52

TEXT/REFERENCE BOOKS:
T/R BOOK TITLE/AUTHORS/PUBLICATION
T Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press
R The Elements of Statistical Learning. Hastie, R. Tibshirani, and J. Friedman, Springer
R . Probabilistic Graphical Models. Koller, and N. Friedman, MIT Press.
R Bishop. C.M., Pattern Recognition and Machine Learning, Springer, 2006.
R Yegnanarayana, B., Artificial Neural Networks PHI Learning Pvt. Ltd, 2009.
R Golub, G.,H., and Van Loan, C.,F., Matrix Computations, JHU Press, 2013.
R Satish Kumar, Neural Networks: A Classroom Approach, Tata McGraw-Hill Education, 2004

4.2 Nominal Rolls

SEC-A

Sno HallTicketNo Name of the Student

1 22Q91A6601 [Link] KUMAR
2 22Q91A6602 [Link]
3 22Q91A6603 [Link]
4 22Q91A6604 ALIGETI RAJESH
5 22Q91A6606 BANAVATH DAYAKAR
6 22Q91A6607 BANDI . NARENDRA
7 22Q91A6608 [Link]
8 22Q91A6609 BHARATH CHANDRA ALAKUNTLA
9 22Q91A6610 BIDUDULA SUPRIYA
10 22Q91A6611 BODDU ANKITA
11 22Q91A6612 BOGUDAMIDA HARIKRISHNA
12 22Q91A6614 BURUSU SASI KIRAN
13 22Q91A6615 [Link]
14 22Q91A6616 CHINTHA NIKHIL
15 22Q91A6617 PAVANI CHOUDAWARAPU
16 22Q91A6618 CHUKKALA ASHRITHA
17 22Q91A6619 EDUNOORI NARESH
18 22Q91A6620 GADDAM SAITEJA
19 22Q91A6621 [Link]
20 22Q91A6622 [Link]
21 22Q91A6623 GOPAGONI PADMAJA
22 22Q91A6624 GOVU PRASAD
23 22Q91A6625 GUGULOTHU VIJAYKUMAR
24 22Q91A6626 [Link] SIDDAPPA
25 22Q91A6627 [Link]
26 22Q91A6628 K JAHNAVI
27 22Q91A6629 KADUMURI DINESH REDDY
28 22Q91A6630 KANUKUNTLA SHIVASAI
29 22Q91A6631 KOLIPAKA RAJU
30 22Q91A6632 KONDAPALLY CHETAN
31 22Q91A6633 KOTAM SHIVANI
32 22Q91A6634 K Abhinav
33 22Q91A6635 KURUVA VINOD
34 22Q91A6636 [Link] KUMAR
35 22Q91A6637 [Link]
36 22Q91A6638 MADDE NIKHILESHWAR
37 22Q91A6639 MAHTHMA GANESH
38 22Q91A6640 MANI KULSHRESTHA
39 22Q91A6641 MOHAMMAD ALIPASHA
40 22Q91A6642 MOUTAM KARTHIK
41 22Q91A6643 MUGALA BHAVITHA GAYATHRI
42 22Q91A6644 NARA SRIHARSHITHA
43 22Q91A6645 NAREDDY POOJITHA
44 22Q91A6646 PALTHIYA SHIRISHA
45 22Q91A6647 PANTANGI DRUVIKA
46 22Q91A6648 PARNANDI VISHNU VARDHAN
47 22Q91A6649 PEDDI MAHESH REDDY
48 22Q91A6650 PEESARI NIHARIKA REDDY
49 22Q91A6653 PUSULURU JETENDRA SAI
50 22Q91A6654 R KARTHIKEYAN
51 22Q91A6655 R VENKATESH
52 22Q91A6656 SEGGEM RAMANA
 53 22Q91A6657 SHESHAGONI AVINASH
54 22Q91A6658 [Link]
55 22Q91A6659 [Link]
56 22Q91A6660 TUMMALA VASUDHA KRISHNA
57 22Q91A6661 TUTKUR SAKETH REDDY
58 22Q91A6662 VANKINIKI PRITHI
59 22Q91A6663 VELPULA MANISHA
60 22Q91A6664 YEDDULA ESWAR YADAV
61 23Q95A6601 CHILUKA KISHORE
62 23Q95A6602 DEVULAPALLY SHIVA KUMAR
63 23Q95A6603 JANGILI SHIVA CHARAN
64 23Q95A6604 MATTA BHAVYA
65 23Q95A6605 SIRALAPU ADARSH
66 23Q95A6606 VADLAVIKRANTH
67 23Q95A6607 VANAM SUMANTH

SEC -B

S. No. HT No. Name of the Student

1 22Q91A6665 AISHI JAIN
2 22Q91A6666 AKSHEETHA . R
3 22Q91A6667 AKULA GANESH
4 22Q91A6668 ALUGUTA MURALI
5 22Q91A6669 ALURI SRAVANTHI
6 22Q91A6670 ANNARAM POOJITHA
7 22Q91A6672 BALUGARI MOUNIKA
8 22Q91A6673 BEJJANKI SANJAY KUMAR
9 22Q91A6674 BODDU SAI PRASAD
10 22Q91A6675 BODINGARU DHRUVA KUMAR REDDY
11 22Q91A6676 BORAPUREDDY KOWSHIK
12 22Q91A6677 BURA VYSHNAVI
13 22Q91A6678 CHINNA CHENNA REDDY GARI SAIMOKSHITHA
14 22Q91A6679 CHITTOJU UMA MAHESHWARI
15 22Q91A6680 DASARI KALYAN
16 22Q91A6681 DUGGONDI VINUTHNA
17 22Q91A6682 ELLULLA DEEPIKA
18 22Q91A6684 GADHAM MAHESH
19 22Q91A6685 GAJULA NIKHIL
20 22Q91A6686 GHODKE RAKSHITHA
21 22Q91A6687 GOLLA ABHIGNA
22 22Q91A6688 GOSULA GIREESH KUMAR
23 22Q91A6689 GUGULOTH SAI KUMAR
24 22Q91A6690 GULLA RAVIKIRAN
25 22Q91A6691 HARSH R BAGTHARIA
26 22Q91A6694 JUVVADI ABHINAYA
27 22Q91A6695 KATIPALLY VAMSHI
28 22Q91A6696 KERELLY AKSHAYA
29 22Q91A6697 MADHARAPU NITHIN KUMAR
30 22Q91A6698 [Link]
31 22Q91A6699 MEDAGANI AMARAKUMAR
32 22Q91A66A0 MOHAMMAD AMAAN FARDHEEN.
33 22Q91A66A1 MUNNURU SRIRAM KUMAR
34 22Q91A66A2 NANGNURI NIKHITHA
35 22Q91A66A3 NARSINGI SHARAN BHUSHAN
36 22Q91A66A4 NERELLA SHIVARAMAKRISHNA
37 22Q91A66A5 NETHARI THARUN
38 22Q91A66A6 NUKALA SANDEEP
39 22Q91A66A7 DIMPLE YADAV
40 22Q91A66A8 [Link] REDDY
41 22Q91A66A9 PADILOJU PAVAN
42 22Q91A66B0 PALLE RAMYASRI
43 22Q91A66B1 PANDUGA HAREESHWER REDDY
44 22Q91A66B2 PENTE TRISHANK
45 22Q91A66B3 PERUMALA GUNARANJAN
46 22Q91A66B4 PULASANI MANISH REDDY
47 22Q91A66B5 PURUSHOTTAM RAJPUROHITH
48 22Q91A66B6 RAJOJU VARSHA
49 22Q91A66B7 RAGIPHANI DILEEP KUMAR
50 22Q91A66B8 RAVULA RATHNAVENI
51 22Q91A66B9 RAYALA VEERANJANEYULU
52 22Q91A66C0 REDDY SRUTHI
53 22Q91A66C1 SALLA SUMANGALI
54 22Q91A66C2 SHAIK ARIF
55 22Q91A66C3 SUNKA VIJETHA
56 22Q91A66C4 TELAGAMSETTY JYOTHIKA
 57 22Q91A66C5 THAKUR SAHIL SINGH
58 22Q91A66C6 THOTLA VYSHNAVI
59 22Q91A66C7 UPPULA ABHINAY
60 22Q91A66C8 YENDLURI MOHAN DATTA SRI SAI
61 23Q95A6608 DODDALLI LAVANYA
62 23Q95A6609 GADDAM MANOJ KUMAR REDDY
63 23Q95A6610 MOHAMMED IRFANULLA SHARIF
64 23Q95A6611 S BHARAT KUMAR
65 23Q95A6612 THODETI TARUN
66 23Q95A6613 THUNGAPINDI PRANAY
67 23Q95A6614 YERRA ABHINAV

SEC - C

ROLL
SNO NUMBER STUDENT NAME
1 22Q91A66C9 AKHIL KUMAR JHA
2 22Q91A66D0 ALAGANDULA DEEPAK MURALI
3 22Q91A66D1 ALLE MEGHANA
4 22Q91A66D2 ALLEM RITHVIK REDDY
5 22Q91A66D3 ARIBABHUVAN TEJA
6 22Q91A66D4 BADDAM SNEHA
7 22Q91A66D5 BEECHUPALLY AKASH
8 22Q91A66D7 BOJJA KATHAVEERYA ARJUN
9 22Q91A66D8 CHIKALAMMETLA KRISHNA PRIYA
10 22Q91A66E0 DHARLAPALLY ROHAN
11 22Q91A66E1 DOMBALE RAVIKANTH
12 22Q91A66E2 DONTINENI MIDHILESH
13 22Q91A66E3 DUNDIGALLA ASHRITHA
14 22Q91A66E4 GAJULA CHAREETH KUMAR
15 22Q91A66E5 GANGAPURAM VIJAYASIMHA REDDY
16 22Q91A66E6 JERIPOTHULA KAVYA
17 22Q91A66E7 JOGULLA MALLIKARJUN
18 22Q91A66E8 KALLURI SAKETH REDDY
19 22Q91A66E9 KAMADRI SAI SUHARSH
20 22Q91A66F0 KANKANALA KAVYA
21 22Q91A66F1 KANKATI SOUMYA
22 22Q91A66F3 KENCHE ABHIRAM
23 22Q91A66F4 KOKKONDA SATHVIKA
24 22Q91A66F5 KONDRU VIKAS
25 22Q91A66F6 KORVA SRI KEERTHI
26 22Q91A66F7 KOTHAPALLI SINDHU
27 22Q91A66F8 LANDE AISHWARYA
28 22Q91A66F9 LAVUDI PAVAN KALYAN
29 22Q91A66G0 MADAKANTI SONU
30 22Q91A66G1 MADAVI TEJA
31 22Q91A66G2 MADUNALA VAISHNAVI
32 22Q91A66G3 MAHESHWARAM NAVYA
33 22Q91A66G4 MALISHETTI VIVEK
34 22Q91A66G5 MANNEPALLI LAHARI
35 22Q91A66G6 MD RIZWANUDDIN
36 22Q91A66G7 MP VENKATA SAI CHAITANYA
37 22Q91A66G8 MULLAPARTI ANITHA
38 22Q91A66G9 N. PARTHIBAN
39 22Q91A66H0 NADIMETLA KEETHANA
40 22Q91A66H1 NENAVATH ANJU
41 22Q91A66H2 PADALA SAI RAMAKRISHNA
42 22Q91A66H3 [Link] SAI NIPUN
43 22Q91A66H4 [Link] KUMAR REDDY
44 22Q91A66H5 PONNA SRINIDHI
45 22Q91A66H6 PUNDRU SAHITH REDDY
46 22Q91A66H7 R. PRAVEEN REDDY
47 22Q91A66H8 SHAIK KHALEEL
48 22Q91A66H9 SIRIMILLA SRI LAXMI
49 22Q91A66I0 SYED RIZWAN
50 22Q91A66I1 [Link]
51 22Q91A66I2 T JOHN DEVA KUMAR
52 22Q91A66I4 THOTA SRIJA
53 22Q91A66I5 THOUTAM YASHWANTH
54 22Q91A66I6 UPPALA THRINATH
55 22Q91A66I7 VEERAPURAM VIVEK VARDHAN
56 22Q91A66I8 VISHWANATHAM NIKHIL
57 22Q91A66I9 [Link]
58 22Q91A66J0 YENUGULA UDAY
59 23Q95A6615 DANDAY POOJA
60 23Q95A6616 G DINESH KUMAR REDDY
61 23Q95A6617 GALIPELLI VISHNU VARDHAN
62 23Q95A6618 REVELLI LOKESH
63 23Q95A6619 VANGARA SHANMUKESHWAR
64 23Q95A6620 VOJJALA CHANDRA SHEKAR
COs to POs & PSOs mapping matrix

COURSE PRE-REQUISITES:
[Link] COURSE NAME DESCRIPTION SEM

AM701 DEEP LEARNING

PC
Basic machine learning concepts and probability 1

COURSE OBJECTIVES:
1 To understand deep Learning algorithms and their applications in real-world data

COURSE OUTCOMES:
PO
SNO DESCRIPTION
MAPPING
1 Understand machine learning basics and neural networks

2 Understand optimal usage of data for training deep models

3 Apply CNN and RNN models for real-world data
4 Evaluate deep models
5 Develop deep models for real-world problems

GAPS IN THE SYLLABUS - TO MEET INDUSTRY/PROFESSION REQUIREMENTS:

SNO DESCRIPTION PROPOSED ACTIONS PO

Syllabi often emphasize theoretical knowledge, Seek internships, apprenticeships, or co-op

1 with practical exposure limited to lab exercises programs to gain experience with actual
or simulations. industry challenges.
Employers need job-ready graduates who can Build a portfolio of personal projects to
apply their knowledge to real-world projects showcase practical skills to potential
2 and technologies. employers.
Participate in hackathons, industry workshops,
and case study competitions

PROPOSED ACTIONS:
TOPICS BEYOND SYLLABUS/ASSIGNMENT/INDUSTRY VISIT/GUEST LECTURER/NPTEL, ETC

TOPICS BEYOND SYLLABUS/ADVANCED TOPICS/DESIGN:

SNO Topic PO
Recurrent and Recursive Nets
Unfolding Computational Graphs, Recurrent Neural Networks, Bidirectional RNNs,
1 Encoder-Decoder
Sequence-to-Sequence Architectures, Deep Recurrent Networks, Recursive Neural
Networks

WEB SOURCE REFERENCES:

1 [Link]
syllabus-neural-networks/119307414
2 [Link]
3 [Link]

DELIVERY/INSTRUCTIONAL METHODOLOGIES:

CHALK & TALK STUD. ASSIGNMENT WEB RESOURCES

LCD/SMART BOARDS STUD. SEMINARS ☐ ADD-ON COURSES

ASSESSMENT METHODOLOGIES-DIRECT

ASSIGNMENTS  STUD. SEMINARS  TESTS/MODEL EXAMS  UNIV. EXAMINATION

STUD. LAB PRACTICES  STUD. VIVA  MINI/MAJOR PROJECTS  CERTIFICATIONS

☐ ADD-ON COURSES ☐ OTHERS

ASSESSMENT METHODOLOGIES-INDIRECT

ASSESSMENT OF COURSE OUTCOMES

STUDENT FEEDBACK ON FACULTY (TWICE)
(BY FEEDBACK, ONCE)

☐ ASSESSMENT OF MINI/MAJOR PROJECTS BY EXT.

☐ OTHERS
EXPERTS

Prepared by Approved by
(K. LOKESH) (HOD)
 Course Outcome (CO) Mapped Program Outcomes (POs)
PO1 (Engineering Knowledge), PO2 (Problem
CO1: Understand the fundamentals of
Analysis), PO4 (Investigations of Complex
deep learning and neural networks
Problems)
CO2: Apply various architectures like PO1, PO2, PO3 (Design/Development of
CNN, RNN, and Autoencoders Solutions), PO5 (Modern Tool Usage)
CO3: Analyze and evaluate deep learning
PO2, PO4, PO5
models for performance and accuracy
CO4: Implement deep learning solutions
PO3, PO5, PO6 (Engineer and Society), PO12
using frameworks like TensorFlow or
(Life-long Learning)
PyTorch
CO5: Explore applications of deep
PO6, PO7 (Environment and Sustainability), PO11
learning in NLP, computer vision, and
(Project Management), PO12
robotics

4.3 COs to POs & PSOs mapping matrix

PROGRAMME:
DEGREE: BTECH
COMPUTER SCIENCE AND ENGINEERING(AIML)
COURSE: DEEP LEARNING SEMESTER: IV/ I L T P C: 3 0 0 3
COURSE CODE: AM701PC
COURSE TYPE: CORE
REGULATION: R22

COURSE OUTCOMES:
PO
COs DESCRIPTION
MAPPING
CO1 Understand the fundamentals of deep learning and neural networks 1,2,4
CO2 Apply various architectures like CNN, RNN, and Autoencoders 1,2,3,5
CO3 Analyze and evaluate deep learning models for performance and accuracy 2,4,5
 CO4 Implement deep learning solutions using frameworks like TensorFlow or PyTorch 3,5,6
CO5 Explore applications of deep learning in NLP, computer vision, and robotics 6,7,11,12

POs PSOs

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2

CO1 1 2 3 √ √

CO2 1 2 3 4 √ √

CO3 1 2 3 √ √

CO4 1 2 3 √

CO5 1 2 3 4 √ √

Avg.

Here in the table, ‘3’ corresponds to a high correlation; ‘2’ corresponds to a medium correlation, and ‘1’
corresponds to a low correlation, between CO and PO/PSO

Prepared by Approved by
(K. LOKESH) (HOD)

4.4 Class time table and

Individual Time Table
 I II III IV V VI

MON DL(C) DL(A) PROJ -A PROJ -A SPORTS

TUES DL(B) DL(A) DL- (C)

WED DL(B) DL(A)

THU DL- (C) DL(A) DL(B)

FRI DL- (C) DL(B) DL(A)

SAT
DL(B) DL- (C) COUNC

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING(AIML)

LESSON PLAN: 2024 -25

Academic Year 2025-2026 Class IV -AIML A B C

DEEP LEARNING Subject Code &

Subject Name
Regulation
AM701PC & R22
 Faculty Name MR KONATALA LOKESH Total No. of Periods 58

Commencement of Completion of
23/ 07 /2025 19/ 11 /2025
Instruction Instruction

Date of I MID Exam 17/ 09/ 2025 Date of II MID Exam 19/ 11 /2025

Prerequisites: basic on machine learning and probability and statistics

Course Objectives: To understand deep Learning algorithms and their

applications in real-world data

Date of Princip
Reason
completion al
Week Unit Lectur for
Topic
No. No. e No. deviati
Propose
Actual on HOD
d

UNIT – I

1 Machine Learning Basics

Learning Algorithms, Capacity, Design,
2 Overfitting and Underfitting,
Hyperparameters and Validation Sets,
Estimators, Bias and Variance,
01 I 3
Maximum Likelihood Estimation, 23/07/20
Bayesian Statistics, 25
4 Supervised Learning Algorithms,
Unsupervised Learning Algorithms,
Stochastic Gradient Descent, Building a
5 Machine Learning Algorithm,
Challenges Motivating Deep Learning

Deep Feedforward Networks Learning

1
XOR, Gradient-Based Learning, Hidden 30/07/20
02 I
Units, Architecture 25
2 Back-Propagation and Other
Differentiation Algorithms
Regularization for Deep Learning
1
Parameter Norm Penalties, Norm
Penalties as Constrained Optimization,
Regularization and Under- Constrained
2
Problems, Dataset Augmentation, Noise 31/07/20
03 II
Robustness, 25
Semi-Supervised Learning, Multi-
3
Task Learning, Early Stopping,
Parameter Tying and Parameter Sharing,
4 Sparse Representations, Bagging and
Other Ensemble Methods, Dropout,
 Adversarial Training, Tangent Distance,
1 Tangent Prop, and Manifold Tangent
Classifier, Optimization for Training
Deep Models, Learning vs Pure
2 Optimization, Challenges in Neural 06/08/20
04 II 25
Network Optimization,
Basic Algorithms, Parameter
3 Initialization
Strategies, Algorithms with Adaptive
Learning Rates
Convolutional Networks
1
The Convolution Operation, Motivation,
Pooling,
2 Convolution and Pooling as an Infinitely
Strong Prior,
07/08/20
05 III 3 Variants of the Basic Convolution
25
Function,
Structured Outputs, Data Types,
4
Efficient Convolution Algorithms,

5 Random or Unsupervised Features

Recurrent and Recursive Nets

Unfolding Computational Graphs,
1
Recurrent Neural Networks,
Bidirectional RNNs, Encoder-Decoder 01/10/20
06 IV
Sequence-to-Sequence 25
2 Architectures, Deep Recurrent
Networks, Recursive Neural Networks,
3 The Challenge of Long-Term
Dependencies, Echo State Networks,
1 Leaky Units and Other Strategies for
Multiple Time Scales,
01/11/20
07 IV 2 The Long Short-Term Memory and
25
Other Gated RNNs,
3 Optimization for Long-Term
Dependencies, Explicit Memory
1 Practical Methodology: Performance
Metrics, Default Baseline Models,
2 Determining Whether to Gather More
08 V Data, Selecting Hyperparameters,
3 Debugging Strategies, Example: Multi-
Digit Number Recognition
4 Applications: Large-Scale Deep
Learning, Processing,
1 Other Applications, Computer Vision,
18/11/20
09 V 25
2
Speech Recognition, Natural Language

Course Outcomes: Upon the completion of the subject, the student will be able to
  Understand machine learning basics and neural networks
 Understand optimal usage of data for training deep models
 Apply CNN and RNN models for real-world data
 Evaluate deep models
 Develop deep models for real-world problems

TEXT BOOKS:

1. Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press.

REFERENCES:
1. The Elements of Statistical Learning. Hastie, R. Tibshirani, and J. Friedman, Springer.

2. Probabilistic Graphical Models. Koller, and N. Friedman, MIT Press.

3. Bishop. C.M., Pattern Recognition and Machine Learning, Springer, 2006.

4. Yegnanarayana, B., Artificial Neural Networks PHI Learning Pvt. Ltd, 2009.

5. Golub, G.,H., and Van Loan, C.,F., Matrix Computations, JHU Press, 2013.

6. Satish Kumar, Neural Networks: A Classroom Approach, Tata McGraw-Hill Education, 2004.

Signature of the
Signature of the Faculty
HOD
[ Mr. K. Lokesh ]
with date
 LECTURE NOTES

1. UNIT WISE LECTURE NOTES

2. Add on Course Material/ Content Beyond the Syllabus

 QUESTION BANK
1. Unit Wise Question Bank
UNIT – 1

1
UNIT- II
1
UNIT- III
1.
UNIT-IV
UNIT-V
2. University Question Papers/ Previous Year QP