Machine learning and artificial intelligence
1. INTRODUCTION
1.1 Journal Overview
This Journal is mainly focused about Machine
learning and artificial intelligence. This journal is a reflective write-up on
what the webinar was about, what was learnt from it and how the knowledge
gained from it can be applied to my future career.
1.2 List of Acronyms and Abbreviations
AI - Artificial intelligence
ML – Machine
Learning
2. Machine
learning and artificial intelligence
Intelligence is
the ability to think, to learn from experience, to solve problems, and to adapt
to new situations.
Artificial intelligence (AI) refers to the simulation of
human intelligence in machines that are programmed to think like
humans and mimic their actions. The term may also be applied to any machine
that exhibits traits associated with a human mind such as learning and problem-solving.
2.2 Learning Outcome
AI is transforming the world around us, creating an
avenue to innovation across all sectors of the global economy. Today, AI can
interact with humans through natural language; identify bank fraud and protect
computer networks; drive cars around city streets; and play complex games like
chess and Go. Machine-learning is offering solutions to many complex problems
around us where analytical solutions may be too expensive or practically
impossible.
Artificial
intelligence (AI) refers to the simulation of
human intelligence in machines that are programmed to think like
humans and mimic their actions. The term may also be applied to any machine
that exhibits traits associated with a human mind such as learning and
problem-solving.
2.3 What
is Intelligence?
Intelligence has
been defined in many ways: the capacity for logic, understanding,
self-awareness, learning, emotional knowledge, reasoning, planning, creativity,
critical thinking, and problem-solving.
2.4 Artificial Intelligence
Artificial intelligence (AI) refers to the simulation of
human intelligence in machines that are programmed to think like
humans and mimic their actions. The term may also be applied to any machine
that exhibits traits associated with a human mind such as learning and
problem-solving.
2.5 Machine Learning
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.
2.6 Deep Learning
Deep learning is a subset of machine learning in
artificial intelligence that has networks capable
of learning unsupervised from data that is unstructured or
unlabeled. Also known as deep neural learning or deep
neural network.
2.7 AI vs Machine Learning vs Deep Learning
Artificial Intelligence is the broader umbrella under which
Machine Learning and Deep Learning come. And you also see in the diagram that
even deep learning is a subset of Machine Learning. So, all three of them AI,
machine learning and deep learning are just the subsets of each other.
2.8 Statical ML Models
A Statistical Model is the use of statistics to build a
representation of the data and then conduct analysis to infer any relationships
between variables or discover insights. Machine Learning is the use of
mathematical and or statistical models to obtain a general understanding of the
data to make predictions.
Statistical modelling is a method of mathematically approximating
the world. Statistical models contain variables that can be used to explain
relationships between other variables. We use hypothesis testing, confidence
intervals etc to make inferences and validate our hypothesis.
The classic example is Regression in which we take a single or
number of variables to find the effect of each explanatory variable to the
independent variable.
A statistical model will have sampling, probability spaces, assumptions,
and diagnostics etc, to make inferences.
We use statistical models to find insights given a particular set
of data. We can conduct modelling on a relatively small set of data just to try
and understand the underlying nature of the data.
Inherently all statistical models are wrong or not perfect. They
are used to approximate reality. Sometimes the underlying assumptions of the
model are far too strict and not representative of reality.
Statistics is a pillar of machine learning. You cannot develop a
deep understanding and application of machine learning without it.
2.9 Neural Networks
Neural networks are a series of algorithms that mimic the
operations of a human brain to recognize relationships between vast amounts of
data. They are used in a variety of applications in financial services, from
forecasting and marketing research to fraud detection and risk assessment.
2.10 Statical ML Models vs Neural Networks
While
a Machine Learning model makes decisions according to what it has
learned from the data, a Neural Network arranges algorithms in a
fashion that it can make accurate decisions by
itself.
Thus, although Machine Learning models can learn from data, in the
initial stages, they may require some human intervention.
Machine
Learning uses advanced algorithms that parse data, learns from it, and use
those learnings to discover meaningful patterns of interest. Whereas a Neural
Network consists of an assortment of algorithms used in Machine Learning for
data modelling using graphs of neurons.
While
a Machine Learning model makes decisions according to what it has learned from
the data, a Neural Network arranges algorithms in a fashion that it can make
accurate decisions by itself. Thus, although Machine Learning models can learn
from data, in the initial stages, they may require some human intervention.
Neural
networks do not require human intervention as the nested layers within pass the
data through hierarchies of various concepts, which eventually makes them
capable of learning through their own errors.
An ML
model works in a simple fashion – it is fed with data and learns from it. With
time, the ML model becomes more mature and trained as it continually learns
from the data. On the contrary, the structure of a Neural Network is quite
complicated. In it, the data passes through several layers of interconnected
nodes, wherein each node classifies the characteristics and information of the
previous layer before passing the results on to other nodes in subsequent
layers.
Since
Machine Learning models are adaptive, they are continually evolving by learning
through new sample data and experiences. Thus, the models can identify the
patterns in the data. Here, data is the only input layer. However, even in a
simple Neural Network model, there are multiple layers.
These
are some of the major differences between Machine Learning and Neural Networks.
Neural Networks are essentially a part of Deep Learning, which in turn is a
subset of Machine Learning. So, Neural Networks are nothing but a highly
advanced application of Machine Learning that is now finding applications in
many fields of interest.
2.11 Machine Learning Everywhere
Most
of the industries dealing with huge amounts of data have now recognized the
value of machine learning. By gleaning hidden insights from this data,
businesses can work more efficiently and can also gain a competitive edge.
Besides, affordable and easy computational processing and cost-effective data
storage options have made it feasible to develop models that quickly and
accurately analyse huge chunks of complex data. Apart from enabling enterprises
to identify trends and patters from diverse data sets, ML also enables
businesses to automate analysis, which was traditionally done by humans. Using
ML organizations can deliver personalized services and differentiated products
that precisely cater to varying needs of the customers. Additionally, ML also
helps companies to identify opportunities that can be profitable in the long
run.
3. Conclusion
The technology is
infusing a deeper intelligence and understanding into the applications that
touch our lives, to dramatically improve our experiences. In addition, it’s
helping to spawn entirely new business innovations and models, such as
autonomous vehicles and virtual personal assistants.
In fact, machine
learning is so prevalent and pervasive that it’s difficult to imagine an
enterprise being able to survive without embracing it in the next five years.
Especially considering predictions of continued global data growth. This is why
it is not only important, but critical to understand the current state of
machine learning and what the future holds.
Skills required
for Machine Learning include programming, probability and statistics, Big Data
and Hadoop, knowledge of ML frameworks, data structures, and algorithms. Neural
networks demand skills like data modelling, Mathematics, Linear Algebra and
Graph Theory, programming, and probability and statistics.
Machine Learning
is applied in areas like healthcare, retail, e-commerce (recommendation
engines), BFSI, self-driving cars, online video streaming, IoT, and
transportation and logistics, to name a few. Neural Networks, on the other
hand, are used to solve numerous business challenges, including sales
forecasting, data validation, customer research, risk management, speech recognition,
and character recognition, among other things.
Comments
Post a Comment