21CSE372T - Deep Learning for Data Analytics

Get Started. It's Free
or sign up with your email address
21CSE372T - Deep Learning for Data Analytics by Mind Map: 21CSE372T - Deep Learning for Data Analytics

1. Course Outcomes

1.1. CO1 - Apply basic concepts in Deep Learning for processing high dimensional data

1.2. CO2 - Incorporate deep learning methods for data analysis

1.3. CO3 - Develop Computer Processing of an image using Deep Neural Network

1.4. CO4 - Analyze various types of video data using Deep Learning techniques

1.5. CO5 - Implement Deep Learning in multimedia data analysis

2. Mapped following PO1, PO2, PO3, PO4, PO5 and SO1, SO2, SO6

2.1. PO1 - Engineering Knowledge:

2.2. PO2 - Problem Analysis

2.3. PO3 - Design and Development of Solutions

2.4. PO4 - Conduct Investigations of Complex Problems

2.5. PO5 - Modern Tool Usage

3. Grading Plan

3.1. Quiz

3.2. CLAT1

3.3. CLAT2

3.4. Mind Mapping

3.5. Notes

3.6. Experiential Learning

4. Rubrics

4.1. Understand high-dimensional data representation, scalability of deep learning methods, and statistical learning for big data analysis

4.2. Optimization and feature selection using deep learning, application of classification, detection, and segmentation techniques

4.3. Techniques for image analysis using CNNs, VGG19, GANs, and U-Net architectures

4.4. Techniques for video data analysis, including discrete action sequences and emotional intelligence

4.5. Feature extraction, multimedia search, representation learning, and large-scale multimedia analysis

5. Unit 1 - Basics of Deep Learning

5.1. Data Analytics Basics

5.1.1. CO1, PO1, SO1

5.2. Enterprise Data Science

5.2.1. CO1, PO1, SO1

5.3. Predictive Analysis

5.3.1. CO1, PO1, SO1

5.4. Scalability of deep learning methods

5.4.1. CO1, PO1,SO1

5.5. Statistical learning for mining and analysis of bigdata (PC5)

5.5.1. CO1, PO5, SO6

5.6. Computational Intelligence Methodology for Data Science

5.6.1. CO1, PO5, SO6

5.7. Challenges in Big Data Analytics

5.7.1. CO1, PO1, SO1

6. Unit 2 - Deep Learning Methodologies

6.1. Optimization for deep learning

6.1.1. CO2, PO2, SO1

6.2. Model structure optimization, large-scale optimization, hyper-parameter optimization

6.2.1. CO2, PO2, SO1

6.3. Feature selection using deep learning

6.3.1. CO2, PO2, SO1

6.4. Novel methodologies using deep learning for classification

6.4.1. CO2, PO2, SO1

6.5. Detection and segmentation

6.5.1. CO2, PO5, SO6

6.6. Single layer convolutional neural network for cardiac disease classification using electro cardiogram signals

6.6.1. CO2, PO5, SO6

6.7. Deep learning on information retrieval and its applications

6.7.1. CO2, PO5, SO6

7. Unit 3 - Deep Learning in Image Analysis

7.1. Computer Processing of an Image: An Introduction

7.1.1. CO3, PO3, SO2

7.2. Case Studies- Apple Leaf Identification based on Optimized Deep Neural

7.2.1. CO3, PO5, SO6

7.3. Network Performance Analysis of VGG19 Deep Learning Network base Brain Image Fusion

7.3.1. CO3, PO5, SO6

7.4. Deep learning-based Tamil vowels prediction using segmentation and U-Net Architecture

7.4.1. CO3, PO3, SO2

7.5. Performance analysis of GAN architecture for effective facial expression synthesis

7.5.1. CO3, PO5, SO6

7.6. Deep CNN for Object classification

7.6.1. CO3, PO5, SO6

8. Unit 4 - Deep Learning in Video Data Analysis

8.1. Introduction to video data analysis

8.1.1. CO4, PO2, SO1

8.2. Uniqueness of video data

8.2.1. CO4, PO2, SO1

8.3. Limitations of video data, conducting video data analysis

8.3.1. CO4, PO2, SO1

8.4. Video data analysis and computer vision

8.4.1. CO4, PO2, SO1

8.5. The future of video data in social science research

8.5.1. CO4, PO2, SO1

8.6. Case study - Discrete action sequences using deep emotional intelligence

8.6.1. CO4, PO5, SO6

9. Unit 5 - Data Analysis for Multimedia Search

9.1. Feature Extraction from Big Multimedia Data

9.1.1. CO5, PO4, SO6

9.2. Representation learning on large and small data

9.2.1. CO5, PO4, SO6

9.3. Concept based and event-based video search

9.3.1. CO5, PO4, SO6

9.4. Feature extraction facing volume, velocity, variety, large scale social multimedia analysis

9.4.1. CO5, PO5, SO6

9.5. Data storage and management for Big Multimedia

9.5.1. CO5, PO4, SO6

9.6. Applications of large-scale multimedia search - Image tagging with Deep Learning: Fine grained Visual Analysis

9.6.1. CO5, PO5, SO6