2. What is an Artificial Neural Network?
• Artificial Neural Networks are the computational models that are
inspired by the human brain.
• Many of the recent advancements have been made in the field of
Artificial Intelligence, including Voice Recognition, Image
Recognition, Robotics using Artificial Neural Networks.
• Artificial Neural Networks are the biologically inspired simulations
performed on the computer to perform certain specific tasks like –
• Clustering
• Classification
• Pattern Recognition
3. • Artificial Neural Networks, in general – is a biologically inspired
network of artificial neurons configured to perform specific tasks.
• These biological methods of computing are considered to be the next
major advancement in the Computing Industry.
4. What is a Neural Network?
• The term ‘Neural’ is derived from the human nervous system’s basic
functional unit ‘neuron’ or nerve cells that are present in the brain and
other parts of the human body.
• A neural network is a group of algorithms that certify the underlying
relationship in a set of data similar to the human brain.
• The neural network helps to change the input so that the network
gives the best result without redesigning the output procedure.
6. • Function of Dendrite
It receives signals from other neurons (accepts input).
• Soma (cell body)
It sums all the incoming signals to generate input (process input).
• Axon Structure
When the sum reaches a threshold value, neuron fires and the signal
travels down the axon to the other neurons (turns the processed inputs
into outputs).
• Synapses Working (Electro chemical contact between neurons)
• The point of interconnection of one neuron with other neurons. The
amount of signal transmitted depend upon the strength (synaptic weights)
of the connections.
• The connections can be inhibitory (decreasing strength) or excitatory
(increasing strength) in nature.
• So, neural network, in general, is a highly interconnected network of
billions of neuron with trillion of interconnections between them.
7. Artificial Neural Network
• Artificial Neural Network (ANNs) are programs designed to solve
any problem by trying to mimic the structure and the function of our
nervous system.
• Neural networks are based on simulated neurons, Which are
joined together in a variety of ways to form networks.
• Neural network resembles the human brain in the following two
ways: -
• A neural network acquires knowledge through learning.
• A neural network’s knowledge is stored within the interconnection
strengths known as synaptic weight.
11. Feed Forward networks
• The data flow from the input to the output units is strictly feed
forward.
• The data processing can extend over multiple layers of units but there
are no feedback connections extending from the outputs of units to the
inputs of units in the same layer or previous layers.
• A multilayer feed-forward network consists of an input layer, one or
more hidden layers and an output layer.
• The neurons in the input layer connect the elements of the input
vector or input pattern to the next layer of the network. The hidden
layers do the processing or computation.
12. • Usually, the activation function of
the hidden layers will be nonlinear.
The output of neurons in each layer
is given as the input to the next
layer. The set of outputs from the
output layer forms the overall
response of the network to the given
input pattern.
13. Recurrent neural network
• It is a dynamic network which contains feedback connections.
• Feedback is said to exist in a dynamic system whenever the output of
an element in the system influences in part the input applied to that
particular element, thereby giving one or more closed paths to the
signal transmission.
• The learning capability of the network has increased with such loops.
After applying a new input, the network output is calculated and fed
back to adjust the input. Then the output is calculated again, and the
process is repeated until the output becomes constant.
17. Training Algorithms For Artificial Neural Networks
• Gradient Descent Algorithm
• This is the simplest training algorithm used in case of supervised
training model. In case, the actual output is different from target
output, the difference or error is find out. The gradient descent
algorithm changes the weights of the network in such a manner to
minimize this mistake.
18. Back Propagation algorithm
• It is an error reducing algorithm used in artificial neural networks.
Artificial neural networks are networks based on the human’s nerve
system.
• These networks contain well defined set of inputs and outputs.
• The network is used to describe the complex relationship between the
inputs and outputs of the network.
• The name comes from the complexity of the network because the
human’s nerves system is so much complex which is known by all of
us.
19. • In this method, the traversal is from output node to various
input nodes and hence called back propagation algorithm.
• At each node the errors are analyzed and the error with
minimum gradient weight is chosen and is referred to as local
minima.
• So at the end of the traversal we will have a set of local
minimas.
• Again an analysis is made on the local minimas and an error
is chosen which have minimum gradient weight. This final
minima is called global minima.
20.
21. Artificial Neural Network Architecture
• A typical Neural Network contains a large number of artificial
neurons called units arranged in a series of layers.
22.
23. • Input layer – It contains those units (Artificial Neurons) which
receive input from the outside world on which network will learn,
recognize about or otherwise process.
• Output layer – It contains units that respond to the information about
how it’s learned any task.
• Hidden layer – These units are in between input and output layers.
The job of the hidden layer is to transform the input into something
that output unit can use in some way.
• Most Neural Networks are fully connected that means to say each
hidden neuron is fully linked to every neuron in its previous
layer(input) and to the next layer (output) layer.
Non-linear : output does not change in direct proportion to a change in any of the inputs
Input layer: This layer consists of the neurons that receive inputs and pass them on to the other layers. The number of neurons in the input layer should be equal to the attributes or features in the dataset.
Output layer: The output layer is the predicted feature and depends on the type of model you’re building.
Hidden layer: In between the input and output layer, there are hidden layers based on the type of model. Hidden layers contain a vast number of neurons which apply transformations to the inputs before passing them. As the network is trained, the weights are updated to be more predictive.
Neuron weights: Weights refer to the strength or amplitude of a connection between two neurons. Weights are often initialized to small random values, such as values in the range 0 to 1.