Assignment # 2
Name Muneeba Gul
Enroll no 929/35
Semester 7th
Department Cs & IT
Subject MIS
Submitted To Sir Rahat Ullah
Assignment Role Of Machine Learning In MIS
Deep learning ? Discuss different models
used for which specific data in brief form
1
Role Of Machine Learning In MIS:
Machine learning is a method of data analysis that automates analytical model building.
It is a branch of artificial intelligence based on the idea that systems can learn from
data, identify patterns and make decisions with minimal human intervention.
In the age of big data, the right information can be used to boost productivity, growth
and efficiency in operations. But this information must be easily accessible and usable
in real time to have value. Advancements like automation, artificial intelligence (AI) and
machine learning are seeing integration into MIS, making it more impactful than ever
before. Plus, the proliferation of big data, analytics and other cloud-based services have
helped increase the relative affordability of and access to MIS for smaller businesses
and organizations.
In addition, the integration of AI and machine learning allows advanced MIS to
accomplish much more without human input or query, such as automatically detecting
and reporting anomalies and predicting potential outcomes according to precedent and
forecasts.
They capture all the data in real-time or near real-time.
Use AI to analyze and understand the content users are managing
Provide meaningful metadata suggestions
Separate business critical data from dark data
Crawl through data repositories.
Find relevant data, make it visible, and attach it to business processes.
Remove information clutter.
Offer users data that is relevant for them now
Understand who the user is.
Provide proactive information that is relevant today (not yesterday or tomorrow).
More relevant search for the user
2
Deep learning
“Deep learning is a branch of machine learning that uses neural networks with many
layers. A deep neural network analyzes data with learned representations similarly to
the way a person would look at a problem,”
“The term ‘deep learning’ refers to the neural networks having many layers that enable
learning.
Neural Network
Most deep learning methods use neural network architectures, which is why deep
learning models are often referred to as deep neural networks.
A neural network is structured like the human brain and consists of artificial neurons,
also known as nodes. These nodes are stacked next to each other in three layers:
The input layer
The hidden layer(s)
The output layer
Data provides each node with information in the form of inputs. The node multiplies the
inputs with random weights, calculates them, and adds a bias. Finally, nonlinear
functions, also known as activation functions, are applied to determine which neuron to
fire.
How Deep Learning Works:
While deep learning algorithms feature self-learning representations, they depend upon
ANNs that mirror the way the brain computes information. During the training process,
algorithms use unknown elements in the input distribution to extract features, group
objects, and discover useful data patterns. Much like training machines for self-learning,
this occurs at multiple levels, using the algorithms to build the models.
Deep learning models make use of several algorithms. While no one network is
considered perfect, some algorithms are better suited to perform specific tasks. To
choose the right ones, it’s good to gain a solid understanding of all primary algorithms.
3
Models of deep learning:
1. Convolutional neural network (CNN)
CNN is one of the most known architectures of DL techniques. This technique is
generally employed for image processing applications. CNN contains three types of
layers with different convolutional, pooling, and fully connected layers (Fig. 1). In each
CNN, there are two stages for the training process, the feed-forward stage, and the
back-propagation stage.
2. Recurrent neural networks (RNN)
RNN is designed to recognize sequences and patterns such as speech, handwriting,
text, and such applications
3. Denoising AutoEncoder (DAE)
DAE has been extended from AE as asymmetrical neural network for learning features
from noisy datasets. DAE consists of three main layers, including input, encoding, and
decoding layers
4. Generative Adversarial Networks (GANs)
GANs are generative deep learning algorithms that create new data instances that
resemble the training data. GAN has two components: a generator, which learns to
generate fake data, and a discriminator, which learns from that false information.
The usage of GANs has increased over a period of time. They can be used to improve
astronomical images and simulate gravitational lensing for dark-matter research. Video
game developers use GANs to upscale low-resolution, 2D textures in old video games
by recreating them in 4K or higher resolutions via image training.
GANs help generate realistic images and cartoon characters, create photographs of
human faces, and render 3D objects.