Machine Learning IT-505

Department of Computer Science, UAF

BS IT 5th Semester
Name: Zaka ullah Tahir
AG no: 2020-ag-6431
Submitted to: Dr. Ahmed Mateen
 Machine Learning Advantages
Machine Learning is a technology that has witnessed an exponential rise in its usage and
popularity in the last couple of years. A huge number of aspirants from around the world are
quickly learning this technology and putting the knowledge to various use. Machine Learning
Engineers are in high demand as a result.

Continuous Improvement
Machine Learning algorithms are capable of learning from the data we provide. As new data
is provided, the model’s accuracy and efficiency to make decisions improve with subsequent
training. Giants like Amazon, Walmart, etc collect a huge volume of new data every day. The
accuracy of finding associated products or recommendation engine improves with this huge
amount of training data available.
Automation for everything
A very powerful utility of Machine Learning is its ability to automate various decision-
making tasks. This frees up a lot of time for developers to use their time to more productive
use. For example, some common use we see in our daily life is social media sentiment
analysis and chatbots. The moment a negative tweet is made related to a product or service of
a Company, a chatbot instantly replies as first-level customer support. Machine Learning is
changing the world with its automation for almost everything we can think of.
Trends and patterns identification
This advantage is a no brainer. All of us interested in Machine Learning technology are well
aware of how the various Supervised, Unsupervised and Reinforced learning algorithms can
be used for various classification and regression problems. We identify various trends and
patterns with a huge amount of data using this technology. For example, Amazon analyses
the buying patterns and search trends of its customers and predicts products for them using
Machine Learning algorithms.
Wide range of applications
Machine Learning is used in every industry these days, for example from Defence to
Education. Companies generate profits, cut costs, automate, predict the future, analyse trends
and patterns from the past data, and many more. Applications like GPS Tracking for traffic,
Email spam filtering, text prediction, spell check and correction, etc are a few used widely
these days. Machine Learning is a branch of Artificial Intelligence, the latest trends and
applications can be found in Artificial Intelligence Trends in 2020.

Machine Learning approaches and its prospects

There are four basic approaches: supervised learning, unsupervised learning, semi-
supervised learning and reinforcement learning. The type of algorithm data scientists choose
to use depends on what type of data they want to predict.

Supervised learning: In this type of machine learning, data scientists supply algorithms
with labeled training data and define the variables they want the algorithm to assess for
correlations. Both the input and the output of the algorithm is specified. Supervised learning
algorithms are good for the following tasks:

 Binary classification: Dividing data into two categories.

 Multi-class classification: Choosing between more than two types of answers.

 Regression modeling: Predicting continuous values.

 Ensembling: Combining the predictions of multiple machine learning models to

produce an accurate prediction.

Unsupervised learning: This type of machine learning involves algorithms that train on
unlabeled data. The algorithm scans through data sets looking for any meaningful connection.
The data that algorithms train on as well as the predictions or recommendations they output
are predetermined. Most types of deep learning, including neural networks, are unsupervised
algorithms. Unsupervised learning algorithms are good for the following tasks:

 Clustering: Splitting the dataset into groups based on similarity.

 Anomaly detection: Identifying unusual data points in a data set.

 Association mining: Identifying sets of items in a data set that frequently occur
together.

 Dimensionality reduction: Reducing the number of variables in a data set.

Semi-supervised learning: This approach to machine learning involves a mix of the

two preceding types. Data scientists may feed an algorithm mostly labeled training data, but
the model is free to explore the data on its own and develop its own understanding of the data
set. From this, the algorithm learns the dimensions of the data set, which it can then apply to
new, unlabeled data. The performance of algorithms typically improves when they train on
labeled data sets. But labeling data can be time consuming and expensive. Semi-supervised
learning strikes a middle ground between the performance of supervised learning and the
efficiency of unsupervised learning. Some areas where semi-supervised learning is used
include:
  Machine translation: Teaching algorithms to translate language based on less
than a full dictionary of words.

 Fraud detection: Identifying cases of fraud when you only have a few positive
examples.

 Labelling data: Algorithms trained on small data sets can learn to apply data
labels to larger sets automatically.

Reinforcement learning: Data scientists typically use reinforcement learning to teach a

machine to complete a multi-step process for which there are clearly defined rules. Data
scientists program an algorithm to complete a task and give it positive or negative cues as it
works out how to complete a task. But for the most part, the algorithm decides on its own
what steps to take along the way. Reinforcement learning is often used in areas such as:

 Robotics: Robots can learn to perform tasks the physical world using this
technique.

 Video gameplay: Reinforcement learning has been used to teach bots to play a
number of video games.

 Resource management: Given finite resources and a defined goal, reinforcement

learning can help enterprises plan out how to allocate resources.

Future Prospect of Machine Learning

The prospect of Machine Learning is not limited to the investment sector. As the Machine
Learning prospect is very high, there are some of the areas where researchers are working
toward revolutionizing the world for the future.

Automotive Industry
The automotive industry is one of the areas where Machine Learning is excelling by changing the
definition of 'safe' driving. There are a few major companies such as Google, Tesla, Mercedes Benz,
Nissan, etc. that have invested hugely in Machine Learning to come up with novel innovations. These
self-driving cars are built using Machine Learning, IoT sensors, high-definition cameras, voice
recognition systems, etc

Robotics
Robotics is one of the fields that always gain the interest of researchers as well as the
common. In 1954, George Devol invented the first robot that was programmable and it was
named as Unimate. After that, in the 21st century, Hanson Robotics created the first AI-robot,
Sophia. These inventions were possible with the help of Machine Learning and Artificial
Intelligence. Researchers all over the world are still working on creating robots that mimic
the human brain. They are using neural networks, AI, ML, computer vision, and many other
technologies in this research. In the future, we may come across robots that would be capable
of performing various tasks similar to a human.

Research
Researchers all over the world are still working on creating robots that mimic the human
brain. They are using neural networks, AI, ML, computer vision, and many other
technologies in this research. In the future, we may come across robots that would be capable
of performing various tasks similar to a human.

Quantum Computing
We are still at an infant state in the field of Machine Learning. One of them that will take
Machine Learning to the next level is Quantum Computing. By using the quantum
phenomenon of superposition, we can create systems (quantum systems) that can exhibit
multiple states at the same time. These quantum systems are built using advanced quantum
algorithms that process data at high speed. Fast processing enhances the processing power of
Machine Learning models. Thus, the future prospect of Machine Learning will accelerate the
processing power of the automation system used in various technologies.

Computer Vision
As the name suggests, computer vision gives a vision to a machine or a computer. Here
comes into our minds what the Head of AI at Google, Jeff Dean, has once said,' The progress
we've made from 26% error in 2011 to 3% error in 2016 is hugely impactful. The way I like
to think is, computers have now evolved eyes that work.' Giving the ability to a machine to
recognize and analyse images, videos, graphics, etc. is the goal of computer vision. The
progress in the field of Artificial Intelligence and Machine Learning has made it possible to
achieve the goal of computer vision faster.