Researchpaper

KIET Group of Institutions, Ghaziabad
Department of computer science and engineering
Internship Report
on
Minor specialisation DSDL project
Aug-Sept
(2023)
Submitted By:
Mahesh Singh
B.Tech/CSE(3rd-B)
2200290100099
Research Paper report
Name of Student Mahesh Singh
Roll No. 2200290100099
Name of Course Minor specialisation

DSDL project
Date of Commencement of 24/08/2023

Training:
Date of Completion of 6/09/2023
Training:
Topic Date
Day 1: Introduction to MS-DSDL 24-08-

2023
Introduction to Data Science
Day 2: Overview of Data Science and

Python and its applications 24-08-2023
Day 3: Data Manipulation and Cleaning 25-08-2023
using Numpy
Day 4: Data Manipulation and Cleaning 28-08-2023
using Pandas
Week 2: Data Visualization and Machine

Learning Basics
Day 5: Introduction to Data Visualization

using Matplotlib and Seaborn 29-08-2023
Day 6: Introduction to ML and its 31-08-2023
Algorithms
Day 7: Model Evaluation and Performance 01-09-2023
Metrics
Week 3: Advanced Machine Learning

Techniques
Day 8: Ensemble Methods: Random Forests 04-09-

and Gradient Boosting 2023
Day 9: Introduction to Deep Learning and 05-09-2023
Neural Networks
Day 10: Deep Learning Frameworks: 06-09-2023
TensorFlow, Pytorch
1. A Decoupled Semantic–Detail Learning

Network for Remote Sensing Object
Detection in Complex Backgrounds
-Hao Ruan
Detecting multi-scale objects in complex backgrounds is a
crucial challenge in remote sensing. The main challenge is that
the localization and identification of objects in complex
backgrounds can be inaccurate. To address this issue,
a decoupled semantic–detail learning network (DSDL-Net) was
proposed. Our proposed approach comprises two components.
Firstly, we introduce a multi-receptive field feature fusion and
detail mining (MRF-DM) module, which learns higher
semanticlevel representations by fusing multi-scale receptive
fields. Subsequently, it uses multi-scale pooling to preserve
detail texture information at different scales. Secondly, we
present an adaptive cross-level semantic–detail fusion (CSDF)
network that leverages a feature pyramid with fusion between
detailed features extracted from the backbone network and high-
level semantic features obtained from the topmost layer of the
pyramid.
The fusion is accomplished through two rounds of parallel
global–local contextual feature extraction, with shared learning
for global context information between the two rounds.
Furthermore, to effectively enhance fine-grained texture features
conducive to object localization and features conducive to object
semantic recognition, we adopt and improve two enhancement
modules with attention mechanisms, making them simpler and
more lightweight.
2. Developing deeper self-directed learning

in database design: Factors that influence
knowledge transfer
-Sukie Van
This paper reports on developing deeper self-directed
learning (DSDL) in a database design course, and on the factors
that hindered and promoted knowledge transfer. Cognitive
load theory and social constructivist theory were incorporated
to enhance DSDL. The population was third-year Computer
Applications Technology (CAT) education students at a South
African university (N=73) enrolled in a database design course.
Convenience sampling was applied.
Data-collection instruments were transfer tests, the
Transferable Learning Orientations tool, and interviews. It was
concluded that the intervention to develop DSDL promoted
transfer of knowledge and skills. The results of this research
can inform instructional practices to promote such transfer in
database design. More research needs to be done to
determine the influence of the suggested strategy to develop
DSDL in terms of other contexts and to refine a strategy to
develop DSDL.
3.Pattern Recognition and Machine

Learning
Christopher M. Bishop
Pattern recognition has its origins in engineering, whereas
machine learning grew out of computer science. However, these
activities can be viewed as two facets of the same field, and together
they have undergone substantial development over the past ten years.
In Bayesian methods have grown from a specialist niche to become
mainstream, while graphical models have emerged as a general
framework for describing and applying probabilistic models. Also, the
practical applicability of Bayesian methods has been greatly enhanced
through the development of a range of approximate inference
algorithms such as variational Bayes and expectation pro- gation.
Similarly, new models based on kernels have had significant impact on
both algorithms and applications.
This new textbook reacts these recent developments while

providing a comprehensive introduction to the fields of pattern
recognition and machine learning. It is aimed at advanced
undergraduates or first year PhD students, as well as researchers and
practitioners, and assumes no previous knowledge of pattern
recognition or - chine learning concepts. Knowledge of multivariate
calculus and basic linear algebra is required, and some familiarity with
probabilities would be helpful though not essential as the book
includes a self-contained introduction to basic probability theory.
4.DESIGN OF THE DISTRIBUTED SPATIAL DATA

LIBRARY (DSDL) FOR THE WATER RESOURCES
Douglas D. Nebert
The conceptual design of the Distributed Spatial Data Library
(DSDL) is being implemented to serve the digital spatial data needs of
the Water Resources Division through the use of public-domain data
discovery programs and integration with existing GIS software. Spatial
data, detailed documentation, data dictionary, and GIS-related
programs are all being made available through the DSDL project to
encourage re-use of data and applications programs within the
Division.
Technologically, the solutions presented by the DSDL project are

easily achievable with an understanding of the inner workings of a GIS
software package and GIS techniques are used in the field. Without
the necessary policy framework, also described in this report, the
implementation of the DSDL project would be a greatly diminished
success. Inasmuch as the DSDL model is being reviewed as a prototype
by the Federal Geographic Data Committee and is being reviewed by
the U.S. Environmental Protection Agency, the technical and policy
framework are achieving more widespread recognition as a model
spatial data management system.
5.Role of Chatgpt in Computer programming

Som Biswas
The abstract introduces ChatGPT, an advanced language model
developed by OpenAI, and highlights its vital role in the realm of
computer programming. ChatGPT has been extensively trained on
diverse text sources, endowing it with the capability to perform a wide
range of programming-related tasks. These tasks encompass code
completion, correction, and suggestion, as well as predicting and
providing code snippets, fixing syntax errors, optimizing and
refactoring code, generating missing code, crafting documentation,
building chatbots, converting text into executable code, and
responding to technical queries.
The results of employing ChatGPT are significant. It excels at

offering users explanations, examples, and guidance, facilitating their
comprehension of intricate concepts, helping them locate pertinent
resources, and aiding in the resolution of technical problems. This
leads to enhanced satisfaction with support services and reinforces
the reputation of organizations as authorities in their fields.
In conclusion, ChatGPT emerges as a potent and versatile tool for

the domain of computer programming. Its multifaceted capabilities
make it invaluable for developers and users, streamlining a variety of
tasks and improving overall efficiency and accuracy. Whether as an
educational resource or a programming assistant, ChatGPT
significantly contributes to the programming landscape.

Researchpaper

Uploaded by

Copyright:

Available Formats

Researchpaper

Uploaded by

Document Information

Original Title

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

Researchpaper

Uploaded by

Copyright:

Available Formats

KIET Group of Institutions, Ghaziabad

Department of computer science and engineering

Roll No. 2200290100099

Name of Course Minor specialisation

Date of Commencement of 24/08/2023

Day 1: Introduction to MS-DSDL 24-08-

Introduction to Data Science

Day 2: Overview of Data Science and

Week 2: Data Visualization and Machine

Day 5: Introduction to Data Visualization

Week 3: Advanced Machine Learning

Day 8: Ensemble Methods: Random Forests 04-09-

1. A Decoupled Semantic–Detail Learning

2. Developing deeper self-directed learning

3.Pattern Recognition and Machine

This new textbook reacts these recent developments while

4.DESIGN OF THE DISTRIBUTED SPATIAL DATA

Technologically, the solutions presented by the DSDL project are

5.Role of Chatgpt in Computer programming

The results of employing ChatGPT are significant. It excels at

In conclusion, ChatGPT emerges as a potent and versatile tool for

You might also like