Convolutional Neural Network
Abstract
The term Deep Learning or Deep Neural Network refers to Artificial Neural Networks (ANN)
with multi layers. Over the last few decades, it has been considered to be one of the most
powerful tools, and has become very popular in the literature as it is able to handle a huge
amount of data. The interest in having deeper hidden layers has recently begun to surpass
classical methods performance in different fields; especially in pattern recognition. One of the
most popular deep neural networks is the Convolutional Neural Network (CNN).In deep
learning, a convolutional neural network is a class of deep neural networks, most commonly
applied to analyzing visual imagery. It takes this name from mathematical linear operation
between matrixes called convolution. CNN have multiple layers; including convolutional layer,
non-linearity layer, pooling layer and fully-connected layer. The convolutional and fully-
connected layers have parameters but pooling and non-linearity layers don't have parameters.
The CNN has an excellent performance in machine learning problems. Especially the
applications that deal with image data, such as largest image classification data set (Image Net),
computer vision, and in natural language processing (NLP) and the results achieved were very
amazing. In this presentation we will explain and define all the elements and important issues
related to CNN, and how these elements work. In addition, we will also state the parameters that
effect CNN efficiency.
Keywords: Artificial neural networks, machine learning, image classification.
Submitted to: Submitted by:
Abhisek Gour Mahima Kadiyan
Assistance Professor 16UITE9032
Data security in cloud computing
Abstract
This presentation discusses the security of data in cloud computing. It is a study of
data in the cloud and aspects related to it concerning security. The presentation will
go in to details of data protection methods and approaches used throughout the
world to ensure maximum data protection by reducing risks and threats.
Availability of data in the cloud is beneficial for many applications but it poses
risks by exposing data to applications which might already have security loopholes
in them. Similarly, use of virtualization for cloud computing might risk data when
a guest OS is run over a hypervisor without knowing the reliability of the guest OS
which might have a security loophole in it. The presentation will also provide an
insight on data security aspects for Data-in-Transit and Data-at-Rest. The study is
based on all the levels of SaaS (Software as a Service), PaaS (Platform as a
Service) and IaaS (Infrastructure as a Service).
Keywords: Virtualization, Data-in-Transit and Data-at-Rest.
Object-oriented Database
Abstract
Object-oriented database systems (OODBS), which aim at meeting the data
modeling, performance, cooperative design, and version management requirements
of next-generation applications, such as CAD, CAM, CASE, hypermedia, and
expert systems, are discussed. Key features of OODBS are presented, taxonomy of
approaches is provided and architectural and implementation issues, design
alternatives, and tradeoffs are examined. This presentation begins by explaining
object-oriented database management systems (OODBMS) in terms of what is the
value added beyond record-oriented database systems and object-oriented
programming languages. It presents most of the current commercial OODBMS and
several advanced prototypes with particular attention to distinguishing them in
their data models, application interfaces and system architectures. It will also
contrast the OODBMS approach with extended relational systems. A variety of
OODB systems, both research prototypes and commercial systems, are
summarized.
Keywords: Architectural and implementation issues, record-oriented database
systems.
