Introduction of computing
and machine learning by the top
of this lesson, you'll be able to define computing describe the
link between AI and data
science define machine learning describe the link between machine learning computing and data science describe different machine learning
approaches identify the applications of machine learning.
Let's understand how the sphere
of computer science emerged.
Let's first understand.
The reason behind the emergence of AI data economy is one in every of the factors behind the emergence of AI it refers
to what proportion data has
grown over the past few years and the
way way more it can grow within the coming years.
When you observe this graph, you'll be able to clearly understand
how the quantity of knowledge has grown.
You can see that since 2009 the
information volume is increased by 44 times with the assistance of social websites.
The explosion of knowledge has
given rise to a replacement
economy and there's a continuing battle for ownership of knowledge between companies to
derive benefits from it.
Now that you just know that data
has grown at a rapid pace within the
past few years and goes to still grow let's understand the necessity for AI as you recognize, the rise in data volume has given rise to big data which helps
manage huge amounts of knowledge
data science helps analyze that data.
So the science related to data goes toward a replacement paradigm where one can teach machines to find out from data and drive a spread of useful insights giving
rise to AI.
Now, you'll ask what's computer science computing
refers to the intelligence displayed by machines that simulates human and
animal intelligence.
It involves intelligence agents the autonomous entities that perceive their
environment and take actions that maximize their chances of success at a given
goal AI may be a technique that during
a people's computers to mimic human intelligence using logic.
It is a program that may sense
reason and act let's take a look at
a number of the areas where AI is employed AI is
redefining industries by providing greater personalization to users and
automating processes one example of computer
science in practice is self-driving cars self-driving cars are computer
controlled cars that drive themselves in these cars human.
These cars also are referred to as autonomous or
driverless cars.
Let's see how Apple uses AI iPhone users can experience the facility of Siri The Voice it simplifies navigating through
your iPhone because it listens
to your voice commands to perform tasks.
For instance.
You can ask Siri to call your friend or to play music serious fun and is
extremely convenient to use another example is google's alphago, which may be a worm that plays the parlor
game go it's the primary malicious program to defeat a world champion at the traditional Chinese game of Go
Amazon.
Echo is another product.
It's a home controlled chatbot device that responds to humans consistent with what they're saying, it responds by playing
music movies and more if you have
compatible smart home devices, you'll
tell echo to dim the lights or turn appliances on or off you'll be able to use AI and chess and
here is an example of a concierge robot from IBM called IBM Watson.
The IBM Watson AI has typically been within
the headlines for composing music playing chess and even cooking food.
Let's move ahead and appearance
at some sci-fi movies with an idea
of computer science the films
featuring AI reflect the ever-changing spectrum of our emotions regarding the
machines.
We have created humans are fascinated by the concept of computer science.
And this is often reflected within the wide selection of flicks
on AI recommendations systems are employed
by lots of e-commerce
companies.
Let's see how they work Amazon collects data from users and recommends the simplest product per the users buying or shopping
pattern.
For example, after you seek for a particular product within
the Amazon store and add it to your cart Amazon recommends some relevant
products supported your past
shopping and searching pattern.
So before you purchase the chosen product you get
recommendations supported your
interest and there's a break that you just might also
buy the relevant product with the
chosen product.
If not, you've got the prospect to check the chosen
product with the recommended products.
Now, let's move ahead and understand the
connection between AI
machine learning and data science, although
the terms computing AI machine
learning and data science fall within
the same domain and are connected to every other.
They have their specific applications and meaning let's attempt to understand a
bit about each of those
terms AI systems mimic or
replicate human intelligence machine learning provides systems the flexibility to automatically learn
and improve from the experiences without being explicitly programmed data
science is an umbrella term that encompasses data analytics data processing machine learning AI and several other other related disciplines.
Let's examine the flow chart and check out to grasp
the link between AI machine
learning and data science interestingly.
Ml is additionally a component of computing.
So the start is data gathering
and data transformation.
This step basically comes under data science data transformation is that the process of converting data
from one format or structure into another format or structure data
transformation is very important
to activities like data
management and data integration after gathering data, we'd want to use the
information to form
predictions and derive insights so as
to urge predictions out of the info set.
We use machine learning techniques like supervised learning or unsupervised learning on an summary level supervised and
unsupervised learning are the machine learning techniques accustomed extract predictions from a
given data set.
Now, you need to be thinking
where deep learning comes into the
image deep learning could be a
subfield of machine learning involved
algorithms.
It uses artificial neural networks, which are modeled on the structure and
performance of neurons within the
human brain deep learning is simplest
when there's not a transparent structure to the information that you simply can just exploit and
build features around now, the
following step within the
flow chart is to induce insights from predictions
being made so as to try to to so, you would like to use data analysis,
which actually is that the
process under data science.
Now once you are finished all of those you want to
want your data to perform some actions.
This is where AI comes into the image
computing combines predictions
and insights to perform actions supported
the human decision and automatic
decision.
Now, let's move ahead and understand the
link between AI machine
learning and data science.
Let's have a look at the link between computing and machine learning computing is that the engineering of
constructing intelligent machines and programs machine learning provides
systems the flexibility to be told from past experiences
without being explicitly programmed machine learning allows machines to realize intelligence.
Thereby enabling computer science.
Let's now understand the connection
between machine learning and data science data science and machine learning go
hand-in-hand data science helps evaluate data for machine learning algorithms
data science covers the full
spectrum of the information
processing while machine learning has the algorithmic or statistical aspects
data science is that the use of
statistical methods to seek out
patterns within the data
statistical machine learning uses the
identical techniques as data science data science includes various
techniques, like statistical modeling visualization and pattern recognition
machine learning focuses on developing algorithms from the information provided by making predictions.
So what's machine learning
machine learning is that the
capability of a man-made
intelligence system to find out
by extracting patterns from data.
It usually delivers quicker more accurate results to assist you see
profitable opportunities or dangerous risks.
Now, you want to be curious to grasp the features of machine
learning machine learning uses the
information to detect patterns during
a data set and to only
program actions.
It focuses on the event of
computer programs which will
teach themselves to grow and alter
when exposed to new data by employing a
method called reinforcement learning.
It uses external feedback to show
the system to vary its internal
workings so as to guess better
next time it enables computers to seek
out hidden insights using iterative algorithms without being explicitly
programmed machine learning uses algorithms that learn from previous data to assist produce reliable and
repeatable decisions.
It automates analytical model building using the statistical and machine
learning algorithms that tease patterns and relationships from data and express
them as mathematical equations.
Let's understand the difference machine learning approaches.
So what's the particular difference between
traditional programming and machine learning in traditional programming data
and program is provided to the pc.
It processes them and offers the
output.
However, the machine learning approach is
extremely different in machine learning algorithms are applied on the
given data and output the results of
the applied algorithm and calculations may
be a learning model that helps machine to find out from the
information in traditional programming you code the behavior of the
program, but in machine learning you
permit lots of that to
the machine to be told from data
now, let's first understand the normal
programming approach traditionally.
You would hard code the choice
rules for a controversy at hand
evaluate the results of the program and if the results were satisfactory, the
program would be deployed in production.
If the results weren't of course one would review the errors
change the program and evaluate it again, this iterative process continues till
one gets the expected result.
What is the machine learning approach within
the new machine learning approach?
The decision rules don't seem to be
hard-coded.
The problem is solved by training a model with the training data so as to derive or learn an algorithm
that best represents the link
between the input and also the
output this trained model is then evaluated against test data if the results
were satisfactory, the model would be deployed in production and if the results
don't seem to be satisfactory
the training is repeated with some changes machine learning techniques machine
learning uses variety of
theories and techniques from data science.
Here are some machine learning techniques classification categorization
clustering analytic thinking
anomaly detection visualization and decision-making.
Let's study these techniques
classification could be a
technique within which the pc program learns from the info input give thereto so uses this learning to classify new observations classification is employed for predicting discrete
responses.
Classification is employed after we are training a model to
predict qualitative targets categorization may be a technique of organizing data into categories for its best and efficient.
Use it makes free text searches faster and provides a far better user experience clustering could be a technique of grouping a group of objects in such the
simplest way that objects within
the same group are most almost
like one another than to
those in other groups.
It is basically a group of
objects on the premise of
similarity and dissimilarity between them Trent analysis may be a technique geared toward projecting both current
and future movement of events through the
employment of your time
series data analysis.
It represents variations of low frequency and a statistic the high and radio
frequency fluctuations being out anomaly detection may be a technique to spot cases that are unusual within
data.
That is seemingly homogenous.
Anomaly detection is a key for
solving intrusions by indicating a presence of intended or unintended induced
attacks defects faults then on
visualization may be a technique
to present data in an exceedingly
pictorial or graphical format.
It enables decision-makers to determine
analytics presented visually when data is shown within the variety of
pictures.
It becomes easy for users to know
it deciding may be a technique or skill that has you with the flexibility to influence
managerial decisions with data as evidence for those possibilities.
Now, i'm sure you have got an improved understanding of the overview of machine learning.
So let's take a look at some
real-time applications of machine learning AI and machine learning are being increasingly employed in various functions like image processing robotics data processing video games text
analysis and healthcare.
Let's take a look at each of
them in additional details.
So what's image processing?
It is a method to convert a picture into a digital format and
perform some operations thereon.
So on induce an enhanced image
or to extract some helpful information from it, let's take a look at a number of
the samples of image processing
Facebook does automatic face tagging by recognizing a face from a previous
users tagged photos.
Another example is optional character recognition, which scans printed Doc's to
digitize the text self-driving cars are another big example of image processing
auto pilot is an optional drive system for Tesla cars when autopilot is engaged
cars can self steer adjust speed detect nearby obstacles apply the brakes and
park now, let's examine how
robotics uses machine learning robots are machines which will be wont to
do certain jobs.
Some of the samples of robotics
are where a humanoid robot can read the emotions of kinsfolk or an industrial robot is employed for assembling and manufacturing products.
So let's observe some real-time
applications of machine learning.
Let's see what data processing
is.
It is the strategy of analyzing
hidden patterns in data.
Let's observe a number of the applications of knowledge mining it's used for anomaly detection to
detect credit-card fraud and to see
which transactions vary from usual purchasing patterns.
It is also employed in market
basket analysis, which is employed
to detect which items are often bought together.
It is used for grouping where it
classifies users supported their
profiles machine learning is
additionally applied in many video games so as to allow
predictions supported data during a Pokemon go battle.
There is plenty of information to require under
consideration to properly
predict the winner of a battle and this
is often where machine learning becomes useful a machine learning
classifier will predict the results of
the match supported this data.
Let's progress to at least one of the foremost popular applications of
machine learning which is text analysis.
It is the automated process of obtaining information from text one example of
text analysis is spam filtering which is
employed to detect spam in emails.
Another example is sentimental analysis, which is employed for classifying an opinion as positive negative or neutral.
It detects public sentiment in Twitter feed or filters customer complaints.
It is also used for information extraction like extracting specific data address keyword or entities.
There are many applications of machine learning within the healthcare industry identifying disease and diagnosis
drug discovery and manufacturing medical imaging diagnosis.
And so on a number of the businesses that use machine
learning have revolutionized the healthcare industry our google deep mind health
bio beats health fidelity and ginger dot IO