DEEP LEARNING THEORY and LAB PROJECT2 PT2

Deep Learning
Course code PCC-AI-401G

Category Professional Core Course
Course title Deep Learning
L T P Credits
Scheme and Credits
3 0 0 3
Class work 25 Marks
Exam 75 Marks
Total 100 Marks
Duration of Exam 03 Hours
Note: Examiner will set nine questions in total. Question one will be compulsory. Question one will have 6
parts of 2.5 marks each from all units and remaining eight questions of 15 marks each to be set by taking
two questions from each unit. The students have to attempt five questions in total, first being compulsory
and selecting one from each unit.
COURSE OBJECTIVES:
1. Understand the concepts of Neural Networks and Deep Learning
2. Understand Deep neural network and layered learning approach
3. Study and understand CNN and RNN for deep learning
4. Learn and understand Auto Encoders and its applications
5. Understand concept of transfer learning and its applications with keras
Unit-I
Introduction: Feed forward Neural networks, Gradient descent and the back propagation algorithm, Unit
saturation, the vanishing gradient problem, and ways to mitigate it. RelU Heuristics for avoiding bad
localminima, Heuristics for faster training, Nestors accelerated gradient descent, Regularization, Dropout.
Convolutional Neural Networks: Architectures, convolution / pooling layers, normalization, sequence
modeling, applications.
Unit-II
Recurrent Neural Networks: LSTM, GRU, Encoder Decoder architectures. Introduction to Simple DNN
Platform for Deep Learning , Deep Learning Software Libraries, Deep Unsupervised Learning:
Autoencoders, Variational Auto-encoders, Adversarial Generative Networks, Auto-encoder and DBM
Attention and memory models. Dynamic memory networks.
Unit-III
Applications of Deep Learning to Computer Vision: Image segmentation, object detection, automatic
image captioning, Image generation with Generative adversarial networks, video to text with LSTM models,
Attention models for computer vision tasks.
Applications of Deep Learning to NLP: Introduction to NLP and Vector Space Model of Semantics,
Word Vector Representations: Continuous Skip-Gram Model, Continuous Bag-of-Words model (CBOW),
Glove, Evaluations.
Unit-IV
Applications in word similarity, Analogy reasoning: Named Entity Recognition, Opinion Mining using
Recurrent Neural Networks: Parsing and Sentiment Analysis using Recursive Neural Networks: Sentence
Classification using Convolutional Neural Networks: Dialogue Generation with LSTMs, Applications of
Dynamic Memory Networks in NLP, Factoid Question Answering, similar question detection, Dialogue
topic tracking, Neural Summarization.
Suggested References Books:

1. I. Goodfellow, Y. Bengio and A. Courville Deep Learning(1e), MIT Press,2016.
2. T. Hastie, R. Tibshirani, and J. Friedman The Elements of Statistical Learning(2e), Springer,2013.
3. D. Koller, and N. Friedman Probabilistic Graphical Models, MIT Press,2010.
4. S. Haykin, Neural Networks and Learning Machines, PHI, 2016.
5. Ng's Notes on Machine Learning from CS229
6.
Course outcomes:
1. Apply basic mathematical concepts in Deep Learning
2. Work with powerful framework for supervised learning
3. Deal with Convolution Neural Networks
4. Analyze various types efficient data encoders
5. Apply various network models in deep learning
Deep Learning Lab
Course code LC-AI-443G
Category Laboratory Course
Course title Deep Learning Lab
L T P Credits
Scheme and Credits
0 0 2 1
Class work 25 Marks
Exam 25 Marks
Total 50 Marks
NOTE:
1. Lab programs/activities can be designed and developed by the subject faculty using Python,
Python Library/suitable Open Source tools/ software.
2. A min 15 Lab activities will be carried out from the offered course contents of Deep Learning in
the semester.
In this course, various experiments will be performed, covering various Deep Learning techniques. Experiments
covering various deep learning techniques for computer vision, NLP, word vector representations, word similarity,
Analogy reasoning, sentence classifications, questions answering, handwritten digits recognitions, sentiment
analysis using Keras/Tensor Flow etc.
Project-II
Course code LC-AI-441G
Category Laboratory Courses
Course title Project-II
L T P Credits
Scheme and Credits
0 0 6 3
Class work 50 Marks
Exam 50 Marks
Total 100 Marks
Course Objectives:
1. To prepare the student to gain major design and or research experience as applicable to the profession
2. Apply knowledge and skills acquired through earlier course work in the chosen project.
3. Make conversant with the codes, standards, application software and equipment
4. Carry out the projects within multiple design constraints
5. Incorporate multidisciplinary components
6. Acquire the skills of comprehensive report writing
Students will be assigned projects(Applications/Research based) individually or in a group of not more

than 3 students depending on the efforts required for completion of project in the subject(s)/area/ skills
delivered in this semester using current tools/technology(ies).
The project will have 4 stages:

(*Marks for internal evaluation are given in brackets)
1. Synopsis submission (10marks),
2. 1st mid-term progress evaluation (Literature Survey in case of research project) (10 marks)
nd
3. 2 mid-term progress evaluation (Paper Publishing/acceptance in a reputed Journal or Conference
acceptance/ Presenting) (10 marks)
4. Final submission evaluation (20 marks).
The external examiner will evaluate the project on the basis of idea/quality of project, implementation of
the project, project report and/or publication and viva.
Course Outcomes:
Design a system / process or gain research insight into a defined problem as would be encountered in
engineering practice taking into consideration its impact on global, economic, environmental and social
context.
Practical Training-II
Course code LC-CSE-G
Category Laboratory Course
Course title Practical Training-II
Scheme and L T P Credits Remarks- Common

Credits 0 0 0 0 with CSE
Class work -
Exam -
Total -
Duration of Exam -
The evaluation of Practical Training-I will be based on seminar, viva-voce, report submitted
by the students. According to performance, the students are awarded grades A, B, C, F. A
student who is awarded grade is required to repeat Practical Training.
Grades :
Excellent: A
Good : B
Satisfactory: C
Not Satisfactory: F

DEEP LEARNING THEORY and LAB PROJECT2 PT2

Uploaded by

Copyright:

Available Formats

DEEP LEARNING THEORY and LAB PROJECT2 PT2

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

DEEP LEARNING THEORY and LAB PROJECT2 PT2

Uploaded by

Copyright:

Available Formats

Deep Learning

Course code PCC-AI-401G

Suggested References Books:

Students will be assigned projects(Applications/Research based) individually or in a group of not more

The project will have 4 stages:

Scheme and L T P Credits Remarks- Common

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.