Artificial neural networks (ANNs) are a form of artificial intelligence modeled after the human brain. ANNs contain interconnected nodes similar to neurons that can learn patterns from data. They are being applied successfully to problems like image recognition, natural language processing, financial forecasting and more. While ANNs can learn complex patterns, interpret their decisions is difficult and overfitting data is a risk.
WSO2CON 2024 - Freedom FirstâUnleashing Developer Potential with Open Source
Â
ARTIFICIAL NEURAL NETWORK.docx
1. ARTIFICIAL NEURAL NETWORK(ANN)
The term "Artificial neural network" refers to a biologically inspired sub-field
of artificial intelligence modeled after the brain. based on biological neural
networks that construct the structure of the human brain. Similar to a human
brain has neurons interconnected to each other, artificial neural networks also
have neurons that are linked to each other in various layers of the networks.
These neurons are known as nodes.
HISTORY OF ANN:
*The history of neural networking arguably began in the late 1800s with
scientific endeavors to study the activity of the human brain. In 1890, William
James published the first work about brain activity patterns.
In 1943, McCulloch and Pitts created a model of the neuron that is still used
today in an artificial neural network.
*In 1987, the IEEE annual international ANN conference was begun for ANN
scientists. In 1987, the International Neural Network Society(INNS) was
formed, along with INNS neural Networking journal in 1988.
2. ARCHITECTURE OF ANN:
Artificial Neural Network primarily consists of three layers:
Input Layer:
As the name suggests, it accepts inputs in several different formats provided by
the programmer.
Hidden Layer:
The hidden layer presents in-between input and output layers. It performs all the
calculations to find hidden features and patterns.
Output Layer:
The input goes through a series of transformations using the hidden layer, which
finally results in output that is conveyed using this layer.
3. WORKING OF ANN:
Artificial Neural Network can be best represented as a weighted directed
graph.The Artificial Neural Network receives the input signal from the external
source in the form of a pattern and image in the form of a vector. These inputs
are then mathematically assigned by the notations x(n) for every n number of
inputs.
Afterward, each of the input is multiplied by its corresponding weights. All the
weighted inputs are summarized inside the computing unit.
If the weighted sum is equal to zero, then bias is added to make the output non-
zero.Bias has the same input, and weight equals to 1.the total of weighted inputs
is passed through the activation function.The activation function refers to the set
of transfer functions used to achieve the desired output. There is a different kind
of the activation function, but primarily either linear or non-linear sets of
functions. Some of the commonly used sets of activation functions are the Binary,
linear, and Tan hyperbolic sigmoidal activation functions.
TYPES OF ANN:
These are 2 types: 1.FEED BACK ANN
2.FEED FORWARD ANN
4. APPLICATIONS OF ANN:
1. Image Recognition and Computer Vision: Image recognition is one of the
most well-known applications of ANNs. In computer vision, ANNs are used to
identify objects, people, and scenes in images and videos.
2.Speech Recognition and Natural Language Processing (NLP): Speech
recognition and NLP are other popular applications of ANNs. In speech
recognition, ANNs are used to transcribe spoken words into text, while in NLP,
they are used to analyze and understand the meaning of the text.
3.Financial Forecasting and Trading: Financial forecasting and trading are
areas where ANNs are being used to make predictions about market trends and
stock prices.
4.Medical Diagnosis and Treatment Planning: Medical diagnosis and
treatment planning are critical applications of ANNs. In medical diagnosis,
ANNs are used to analyze medical images and patient data to identify diseases
and disorders.
5.Autonomous Vehicles: Autonomous vehicles are one of the most exciting
applications of ANNs. In autonomous vehicles, ANNs are used to analyze
sensor data and make decisions about how the vehicle should respond to its
environment.
6.Natural Language Generation: Natural language generation is a relatively
new application of ANNs that is rapidly gaining popularity. In natural language
generation, ANNs are used to generate text that mimics human writing.
7.Fraud Detection: Fraud detection is an important application of ANNs that is
being used to prevent financial losses and protect businesses and consumers. In
fraud detection.
8.Predictive Maintenance: Predictive maintenance is a growing application of
ANNs that is being used to improve equipment reliability and reduce
downtime.
5. ADVANTAGES OF ANN:
1. Learning Ability â One of the main advantages of ANNs is their ability
to learn and adapt to new situations. They can be trained on large datasets
and learn patterns that are not easily discernible by humans.
2. Non-Linear Relationships â ANNs are capable of learning non-linear
relationships between inputs and outputs, making them useful in a wide
range of applications such as image and speech recognition.
3. Fault Tolerance â ANNs are also able to tolerate faults, meaning that
they can still function correctly even if some of the neurons in the
network are damaged or destroyed.
4. Parallel Processing â Another advantage of ANNs is their ability to
perform many calculations simultaneously, which allows them to process
large amounts of data quickly and efficiently.
DISADVANTAGES OF ANN:
1. Overfitting â ANNs can sometimes become too specialized and only
able to work with a specific type of data. This can lead to overfitting,
where the network becomes so focused on the training data that itâs
unable to generalize to new data.
2. Limited Interpretability â Unlike traditional statistical models, ANNs
are often considered âblack boxes,â meaning we donât always understand
how they arrived at their conclusions. This can be a disadvantage in
situations where we need to know how the network made a particular
decision.
3. Computationally Expensive â Training an ANN can require a lot of
computational power and time, especially for large datasets. This can be a
disadvantage for organizations that donât have access to powerful
computing resources.
4. Data Requirements â ANNs require a large amount of data to learn
effectively. If the dataset is small or biased, the network may not be able
to learn the underlying patterns and relationships between the data points