REGULATIONS AND SYLLABUS
for
certification course on
DEEP LEARNING
(w.e.f 2019-20 admitted batch)
VISAKAPATNAM-530 045
www.gitam.edu
A University Committed to Excellence
DEPARTMENT OF
INFORMATION TECHNOLOGY
Information technology is a highly dynamic and ever-changing field. As the industry
evolves, new types or sets of certifications continue to crop up.
There are myriads of reasons why you should seek out certification in a number of IT-related
programs and software skills, but three reasons are key:
1.Credibility 2.Marketability 3.Personal development
DEEP LEARNING
COURSE DESCRIPTION
Deep Learning is one of the most exciting and promising segments of Artificial
Intelligence and machine learning technologies. This course with Tensor Flow is designed to
help you master deep learning techniques and build using Tensor Flow, an open-source software
library developed by Google for the purpose of conducting machine learning and deep neural
networks. It is one of the most popular software platforms used for deep learning and contains
powerful tools to help you build and implement artificial neural networks. .
Advancements in deep learning are being seen in smart phone applications, creating
efficiencies in the power grid, driving advancements in healthcare, improving agricultural yields,
and help us find solutions to climate change. With this Tensor flow course, you’ll build expertise
in deep learning models, learn to operate Tensor Flow to manage neural networks and interpret
the results. .
REGULATIONS
(w.e.f. 2019-20 admitted batch)
Duration and Class Schedule
This course is offered for one semester
Duration: 2 Months (Thursday, Friday and Saturday each week from 4:00PM to 6:00PM (6
Hours per Week).
The classes are conducted at Department of IT, GITAM Institute of Technology, GITAM
University, Hyderabad Campus.
Total Number of Theory hours are 30
Total Number of Laboratory Hours are 18
Eligibility
The participants must be 3rd Year or Final Students of B.Tech CSE/IT/ECE/EEE/EIE/Mech
or faculty in Engineering / Degree Colleges
Teaching Faculty
Faculty of Department of Information Technology, GITAM Institute of Technology, GITAM
University
Fee Particulars:
Student from GITAM : 3000/-
Faculty of GITAM, Student from other colleges : 3500/-
Others –faculty/Employees : 16000/- + 18% GST as applicable
Evaluation Procedure
A minor examination shall be conducted at the end of each module for 10 Marks (4 X 10 = 40
Marks)
A written examination shall be conducted at the end of the certificate course for 60 Marks
A laboratory examination shall be conducted at the end of the certificate course for 100 Marks
Final Score shall for 100 Marks shall be calculated for the theory course and for the laboratory
course and grade shall be as per below grading system.
Grading System
Based on the student performance a final letter grade will be awarded at the end of the
certificate course. The letter grades and the corresponding grade points are as given in Table
Table: Grades and Grade Points
S.No. Grade Grade Points Absolute Marks
1 O (Outstanding) 10 90 and above
2 A+ (Excellent) 9 80 to 89
3 A (Very Good) 8 70 to 79
4 B+ (Good) 7 60 to 69
B (Above
5 Average) 6 50 to 59
6 C (Average) 5 45 to 49
7 P (Pass) 4 40 to 44
8 F (Fail) 0 Less than 40
9 Ab. (Absent) 0 -
Grade Point Average
A Grade Point Average (GPA) for the course will be calculated according to the formula:
Σ[ C- G ]
GPA = ——————
ΣC
A student who earns a minimum of 4 grade points (P grade) in the final theory and laboratory
examination is declared to have successfully completed the course, subject to securing a GPA of
5 for a pass in the course.
Course Objectives
By the end of the course, students will be able to
understand complexity of Deep Learning algorithms and their limitations
understand modern notions in data analysis oriented computing;
be capable of confidently applying common Deep Learning algorithms in practice
and implementing their own;
be capable of performing distributed computations;
be capable of performing experiments in Deep Learning using real-world data.
Course Outcomes
By the end of this deep learning course with TensorFlow, the student will be able to
Understand the concepts of TensorFlow, its main functions, operations and the
execution pipeline
Implement deep learning algorithms, understand neural networks and traverse the
layers of data abstraction which will empower the student to understand data more
precisely.
Learn topics such as convolutional neural networks, recurrent neural networks,
training deep networks and high-level interfaces
Build deep learning models in TensorFlow and interpret the results
Understand the language and fundamental concepts of artificial neural networks
Troubleshoot and improve deep learning models
Build own deep learning project
Differentiate between machine learning, deep learning and artificial intelligence
SYLLABUS
UNIT 1:
Introduction to TensorFlow :Computational Graph, Key highlights, Creating a Graph,
Regression example, Gradient Descent, TensorBoard, Modularity, Sharing Variables,Keras
Perceptrons: What is a Perceptron, XOR Gate
UNIT 2:
Activation Functions : Sigmoid,ReLU, Hyperbolic Fns,Softmax
Artificial Neural Networks : Introduction, Perceptron Training Rule, Gradient Descent Rule
UNIT 3:
Gradient Descent and Backpropagation: Gradient Descent, Stochastic Gradient Descent,
Backpropagation, Some problems in ANN
Optimization and Regularization :Overfitting and Capacity, Cross Validation, Feature
Selection, Regularization, Hyperparameters
UNIT 4:
Introduction to Convolutional Neural Networks: Introduction to CNNs, Kernel filter,
Principles behind CNNs, Multiple Filters, CNN applications
Introduction to Recurrent Neural Networks: Introduction to RNNs, Unfolded RNNs,
Seq2Seq RNNs, LSTM, RNN applications
UNIT 5:
Deep Learning applications: Image Processing, Natural Language Processing, Speech
Recognition, Video Analytics
Text Book
1. Goodfellow, I., Bengio,Y., and Courville, A., Deep Learning, MIT Press, 2016.
References
1. Bishop, C. ,M., Pattern Recognition and Machine Learning, Springer, 2006.
2. Yegnanarayana, B., Artificial Neural Networks PHI Learning Pvt. Ltd, 2009.
3. Golub, G.,H., and Van Loan,C.,F., Matrix Computations, JHU Press,2013.
4. Satish Kumar, Neural Networks: A Classroom Approach, Tata McGraw-Hill Education,
2004.
