How It Works Aim Focus Conclusion Introduction To Artificial Intelligence

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 8

Introduction

How it works
Aim
Focus
conclusion

Introduction to Artificial Intelligence


Artificial intelligence (AI) is intelligence demonstrated by machines, as opposed to the natural
intelligence displayed by animals including humans. Leading AI textbooks define the field as the
study of "intelligent agents": any system that perceives its environment and takes actions that
maximize its chance of achieving its goals.
According to the father of Artificial Intelligence, John McCarthy, it is “The science and
engineering of making intelligent machines, especially intelligent computer programs”.
Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a
software think intelligently, in the similar manner the intelligent humans think.
AI is accomplished by studying how human brain thinks, and how humans learn, decide, and
work while trying to solve a problem, and then using the outcomes of this study as a basis of
developing intelligent software and systems.

Sub-fields of Artificial Intelligence


AI has been dominant in various fields such as: -
 Neural Networks
 Evolutionary Computation
 Vision
 Robotics
 Expert Systems
 Speech Processing
 Natural Language Processing
 Planning
 Machine Learning

Introduction to neural Network

The definition of a neural network, more properly referred to as an 'artificial' neural network

(ANN), is provided by the inventor of one of the first neurocomputers, Dr. Robert Hecht-Nielsen.

He defines a neural network as:


"...a computing system made up of a number of simple, highly interconnected processing

elements, which process information by their dynamic state response to external inputs."

Neural networks are computing systems with interconnected nodes that work much like neurons

in the human brain. Using algorithms, they can recognize hidden patterns and correlations in raw
data, cluster and classify it, and – over time – continuously learn and improve.

Architecture of neural network (how it works).


The Neural Network architecture is made of individual units called neurons that mimic the
biological behavior of the brain. 

Here are the various components of a neuron.

Input - It is the set of features that are fed into the model for the learning process. For example, the
input in object detection can be an array of pixel values pertaining to an image.

Weight - Its main function is to give importance to those features that contribute more towards the
learning. It does so by introducing scalar multiplication between the input value and the weight
matrix. For example, a negative word would impact the decision of the sentiment analysis model
more than a pair of neutral words.
Transfer function - The job of the transfer function is to combine multiple inputs into one output
value so that the activation function can be applied. It is done by a simple summation of all the
inputs to the transfer function. 

Activation Function - It introduces non-linearity in the working of perceptron’s to consider varying


linearity with the inputs. Without this, the output would just be a linear combination of input values
and would not be able to introduce non-linearity in the network.

Bias - The role of bias is to shift the value produced by the activation function. Its role is similar to
the role of a constant in a linear function.

When multiple neurons are stacked together in a row, they constitute a layer, and multiple layers
piled next to each other are called a multi-layer neural network.

Hidden Layers

The hidden layers are what makes deep learning what it is today. They are intermediate layers that
do all the computations and extract the features from the data.

There can be multiple interconnected hidden layers that account for searching different hidden
features in the data. For example, in image processing, the first hidden layers are responsible for
higher-level features like edges, shapes, or boundaries. On the other hand, the later hidden layers
perform more complicated tasks like identifying complete objects (a car, a building, a person).
Output Layer 

The output layer takes input from preceding hidden layers and comes to a final prediction based on
the model’s learnings. It is the most important layer where we get the final result.

In the case of classification/regression models, the output layer generally has a single node.
However, it is completely problem-specific and dependent on the way the model was built.

Goal of neural network


The aim of Artificial neural network is to realize a very simplified model of the human brain.in this way,
Artificial neural network tries to learn tasks to solve problems mimicking behavior of brain. The brain is
composed by a large set of elements, specialized cells called neurons

Conclusion for artificial neural network


Neural network is suitable for predicting time series mainly because of learning only from examples,
with out any need to add additional information that can bring more confusion than prediction effect.
neural network is able to generalize and are resistant to noise. On the other hand, it is generally not
possible to determine exactly what a neural network learned and it is also hard to estimate possible
prediction errors. How ever neural network were often successfully used for predicting time series. They
are ideal especially when we don’t have any other description of observed series.

Introduction to Evolutionary Computation


Evolutionary Computation is collective name for a range of problem-solving techniques based on
principles of biological evolution, such as natural selection and genetic inheritance. These techniques are
being increasingly widely applied to variety of problem, ranging from practical applications in industry
and commerce to leading -edge scientific research.

Evolutionary computation how it works


Evolutionary computation draws on Charles Darwin’s principles of natural evolution, commonly
known as survival of the fittest. That is, the weakest (less well adapted) members of a species die
off and the strongest survive. Over many generations, the species will evolve to become better
adapted to its environment.

In evolutionary computation, the computer creates a population of potential solutions to a


problem. These are often random solutions, so they are unlikely to solve the problem being
tackled or even come close. But some will be slightly better than others. The computer can
discard the worst solutions, retain the better ones and use them to “breed” more potential
solutions. Parts of different solutions will be combined (this is often called “crossover”) to create
a new generation of solutions that can then be tested and the process begins again.
Another important element of evolutionary computation, as with natural selection, is mutation.
Every so often a small, random change is made to one of the solutions being tested. This means
new potential solutions can be created that wouldn’t be possible from just using crossover.

Goal of Evolutionary computation


The goal of evolutionary computation is to make use of inspiration from nature to solve difficult
computational problems. By using the four algorithms these are Genetic algorithm, genetic
programming, evolutionary programming, and evolutionary strategies.

Conclusion
Evolutionary computation is methodology for solving optimized problems. Those problems are found
numerously in machine learning and artificial intelligence domains. Evolutionary computation
commonly used in these scenarios where classical numerical methods fail to find good solutions.

Introduction to Computer vision


is defined as a field of study that seeks to develop techniques to help computers “see” and
understand the content of digital images such as photographs and videos.

Goal of computer vision


The goal of computer vision is to understand the content of digital images. Typically, this
involves developing methods that attempt to reproduce the capability of human vision.

Understanding the content of digital images may involve extracting a description from the
image, which may be an object, a text description, a three-dimensional model, and so on.

How does Computer Vision work?


 Images on computers are often stored as big grids of pixels. Each pixel is defined as color, stored
as a combination of 3 additive primary colors: RGB (Red Green Blue). These are combined in
varying intensities to represent different colors. Colors are stored inside pixels.
 Let’s consider a simple algorithm to track a bright orange football on a football field. For that,
we’ll take the RGB value of the centermost pixel. With that value saved, we can give a computer
program an image, and ask it to find the pixel with the closest color match. The algorithm will
check each pixel at a time, calculating the difference from the target color. Having looked at
every pixel, the best match is likely a pixel from the orange ball. We can run this algorithm for
every frame of the video and track the ball over time. But, if one of the teams is wearing an
orange jersey, the algorithm might get confused. So, this approach doesn’t work for features
larger than a single pixel, such as edges of objects, which are made up of many pixels.
 To identify these features in images, computer vision algorithms have to consider small regions
of pixels, called patches. For example, an algorithm that finds vertical edges in a scene, to help a
drone navigate safely through a field of obstacles. For this operation, a mathematical notation is
used, which is called a kernel or filter. It contains the values for a pixel-wise multiplication, the
sum of which is saved into the center pixel.
 Earlier, an algorithm called Viola-Jones Face Detection was used, which combined multiple
kernels to detect features of the faces. Today, the newest and trending algorithms on the block
are Convolutional Neural Networks (CNN).

CV applications involve trying to recognize things in images, for example:


 Object Classification: the category of object in image.

 · Object Identification: the type of a given object is the image

 · Object Verification: verify if the object exists in the image

 · Object Detection: try to detect the objects in the given image or video

 · Object Segmentation: What pixels belong to the object in the image?

 ·Object Recognition: What objects are in this image and where are they?

conclusion
 Computer Vision is HARD and require a big effort to start digging deep in that universe, but with
Deep learning methods we can achieve state-of-the-art results on challenging computer vision
problems such as image classification, object detection, and face recognition.

Introduction to robotics
Robotics is a domain in artificial intelligence that deals with the study of creating intelligent and
efficient robots.

Robotics is a branch of AI, which is composed of Electrical Engineering, Mechanical


Engineering, and Computer Science for designing, construction, and application of robots.
Robots are the artificial agents acting in real world environment.

Goal of robotics
Robots are aimed at manipulating the objects by perceiving, picking, moving, modifying the
physical properties of object, destroying it, or to have an effect thereby freeing manpower from
doing repetitive functions without getting bored, distracted, or exhausted.

How robots work


 The robots have mechanical construction, form, or shape designed to accomplish a
particular task.
 They have electrical components which power and control the machinery.
 They contain some level of computer program that determines what, when and how a
robot does something.
Conclusion
 Robots have made life easier and more efficient, but we need to keep in mind that they cannot
replace human intelligence, yet. Robots can’t think or decide, they are just apparatuses to enable
us to complete things. Robots are machines with programmed developments that enable them to
move in specific ways or groupings.

Introduction to Expert systems


Expert systems are special databases which are designed to mimic (copy) the expertise and
knowledge of a human expert in various different subjects.

An expert system is a knowledge-based information system; that is, it uses its knowledge about a
specific area to act as an expert consultant to users. The components of an expert system are a
knowledge base and software modules that perform inferences on the knowledge and offer
answers to a user’s questions. Expert systems provide answers to questions in a very specific
problem area by making human like inferences about knowledge contained in a specialized
knowledge base. Expert systems can provide decision support to end users in the form of advice
from an expert consultant in a specific problem area.

Goal of Expert systems


To provide advice that at least matches in reliability that advice that would be provided upon analysis of
the same data by human expert.
Interact with user through a natural language interface.

When required, provide justification for, and an explanation of, its decision and advice.

Deal effectively with uncertainly and incomplete information.

How expert systems work (architecture).

Knowledge Base: It consists of problem-solving rules, procedures and intrinsic data relevant to
the problem domain.
Working Memory: It refers to task-specific data for the problem under consideration.
Inference Engine: It is a generic control mechanism. It also applies the axiomatic knowledge in
the KB to the task-specific data to arrive at some solution or conclusion.
Conclusion
An expert system is any computer-based decision-making system that is interactive and reliable
to resolve complex problems. An expert system is used for applications such as human resources,
stock market, and so on. Key benefits of expert systems are better decision quality, cost
reduction, consistency, speed, and reliability. An expert system does not give out of the box
solutions, and the maintenance cost is high. 

Introduction to speech processing

Speech processing is the study of speech signals and the processing methods of signals. The
signals are usually processed in a digital representation, so speech processing can be regarded as
a special case of digital signal processing, applied to speech signals. Aspects of speech
processing includes the acquisition, manipulation, storage, transfer and output of speech signals.
The input is called speech recognition and the output is called speech synthesis.

Goal or purpose of Speech processing


Is - To understand speech as a means of communication;
– To represent speech for transmission and reproduction;

– To analyze speech for automatic recognition and extraction of information

– To discover some physiological characteristics of the talker.

How Speech processing works


Speech recognition software works by breaking down the audio of a speech recording into
individual sounds, , analyzing each sound, using algorithms to find the most probable word fit in
that language, and transcribing those sounds into text.
Speech recognition software uses natural language processing (NLP) and deep learning neural
networks. “NLP is a way for computers to analyze, understand, and derive meaning from
human language in a smart and useful way,” according to the Algorithms blog. This means that
the software breaks the speech down into bits it can interpret, converts it into a digital format,
and analyzes the pieces of content.

conclusion

You might also like