Introduction To NN

Nervous system
The nervous system is a network of neurons whose main feature is to generate, modulate
and transmit information between all the different parts of the human body.
This property enables many important functions of the nervous system, such as regulation
of vital body functions (heartbeat, breathing, digestion), sensation and body movements.
Ultimately, the nervous system structures preside over everything that makes us human;
our consciousness, cognition, behaviour and memories.
The nervous system consists of two divisions;

Central nervous system (CNS) is the integration and
command center of the body
Peripheral nervous system (PNS) represents the
conduit between the CNS and the body.
“Neurons are the fundamental unit of the nervous system.”
 Our body is composed of millions to billions of nerve cells.
 Some nerve cells can be comparatively smaller by 0.1

millimeters or can be longer by 1 meter.
 The size of nerve cells is usually based on their functions

i.e how long electrical impulse is transmitted within our
body.
 They are found in the brain, spinal cord and peripheral

nerves.
 For instance, the nerve cell, which transmits the electrical

impulse from our brain to the end of the toe finger may
be the largest nerve cell.
 The size of the nerve cell even varies with the type of
organism.
What is Nerve Cell?
A nerve cell is also known as a neuron. It is mainly involved in receiving and

transmitting information to different parts of the body.
Nerve cell or Neuron is called the main structural and functional units of the
nervous system.
The shape and size of the Neuron generally vary, depending upon the location
and functions.
A group of neurons forms a nerve and the nervous system.

Biological neuron
A biological neuron has a cell body or soma to process the impulses,

dendrites to receive them, and an axon that transfers them to other neurons.
Structure of Nerve Cell or Neuron
The nerve cell is a specialized and individual cell, which forms a nerve.
Basically, the structure of the nerve cell comprises the following parts.
Dendrites
A branch-like structure that functions by receiving messages from other
neurons and allows the transmission of messages to the cell body.
Axon
It is a tube-like structure, which functions by carrying an electrical impulse from
the cell body to the axon terminals and by transmitting the impulse to another
neuron.
Nucleus
Each neuron or a nerve cell has a cell body with a nucleus and other cell
organelles including, the endoplasmic reticulum, Golgi apparatus, mitochondria
and other components.
Synapse
It is also called the nerve ending or nerve junction, which is mainly involved in
permitting the entry of a neuron to move electrical signals from one neuron to
another neuron.
Artificial neurons vs Biological neurons
The concept of artificial neural networks comes from biological neurons found in
animal brains So they share a lot of similarities in structure and function wise.
Structure: The structure of artificial neural networks is inspired by biological

neurons. A biological neuron has a cell body or soma to process the impulses,
dendrites to receive them, and an axon that transfers them to other neurons.
The input nodes of artificial neural networks receive input signals, the hidden
layer nodes compute these input signals, and the output layer nodes compute
the final output by processing the hidden layer’s results using activation
functions.
Neural Network
Artificial Neural Networks
Artificial Neural Networks contain artificial neurons which are called units. These
units are arranged in a series of layers that together constitute the whole Artificial
Neural Network in a system. A layer can have only a dozen units or millions of
units as this depends on how the complex neural networks will be required to
learn the hidden patterns in the dataset.
Commonly, Artificial Neural Network has an input layer, an output layer as well as
hidden layers. The input layer receives data from the outside world which the
neural network needs to analyze or learn about. Then this data passes through
one or multiple hidden layers that transform the input into data that is valuable
for the output layer. Finally, the output layer provides an output in the form of a
response of the Artificial Neural Networks to input data provided.
In the majority of neural networks, units are interconnected from one layer to
another. Each of these connections has weights that determine the influence of
one unit on another unit. As the data transfers from one unit to another, the
neural network learns more and more about the data which eventually results in
an output from the output layer.
Model of a Neuron
Human brain Vs Computer
Brain Computer
The brain has 100 billion neurons which
Today’s computers merely are
form billions of links. Brain is much more
Size Complexity: formed with hundreds of millions
complex than the computer.
of transistors and circuit.
The human brain being biological uses tiny Computer uses electrical energy
chemical reactions to produce its signals. to represent signals. The energy
Brain cells signal each other efficiency of today’s best
electrochemically and enzymatically. The computer is approximately 10-6
Signal & Energy
energy efficiency of the brain is joules per operation per second.
approximately 10-16 joules per operation per
second.
Human brain is slower than computer.

Computers are five to six orders
Typically the events happen in the human
faster than human brain Typically
brain within the range of milliseconds (10-
Speed: 3sec). the events happen in the
computer within the range of
nanoseconds (10-9sec).
It is impossible for the brain to act without
Computers act only on logic. We
emotions. Brains act on emotions, that many
know that computers act
Emotions vs Logic of our actions are based on our emotional
completely on logical bits that are
side.
total absolute.
Human brain learns from environments. Computers just conduct
Capability
programmed instructions.
Activation Functions
Threshold/step Function:
Threshold/step Function: It is a commonly used activation function. As
depicted in the diagram, it gives 1 as output of the input is either 0 or
positive. If the input is negative, it gives 0 as output. Expressing it
mathematically,
The threshold function is almost like the step function, with the only
difference being a fact that \theta is used as a threshold value instead of .
Expressing mathematically,
ReLU (Rectified Linear Unit) Function
ReLU (Rectified Linear Unit) Function: It is the most popularly used

activation function in the areas of convolutional neural networks and
deep learning. It is of the form:
This means that f(x) is zero when x is less than zero and f(x) is equal to x when x is
above or equal to zero. This function is differentiable, except at a single point x =
0. In that sense, the derivative of a ReLU is actually a sub-derivative.
Sigmoid Function:
Sigmoid Function: It is by far the most commonly used activation function in

neural networks. The need for sigmoid function stems from the fact that many
learning algorithms require the activation function to be differentiable and
hence continuous. There are two types of sigmoid function:
1. Binary Sigmoid Function
A binary sigmoid function is of the form:

, where k = steepness or slope parameter, By varying the value of k, sigmoid
function with different slopes can be obtained. It has a range of (0,1). The slope
of origin is k/4. As the value of k becomes very large, the sigmoid function
becomes a threshold function.
2. Bipolar Sigmoid Function
A bipolar sigmoid function is of the form
The range of values of sigmoid functions can be varied depending on the

application. However, the range of (-1,+1) is most commonly adopted.
Hyperbolic Tangent Function
Hyperbolic Tangent Function: It is bipolar in nature. It is a widely

adopted activation function for a special type of neural network
known as Backpropagation Network. The hyperbolic tangent
function is of the form
This function is similar to the bipolar sigmoid function.

Introduction To NN

Uploaded by

Copyright:

Available Formats

Introduction To NN

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Introduction To NN

Uploaded by

Copyright:

Available Formats

Nervous system

The nervous system consists of two divisions;

 Our body is composed of millions to billions of nerve cells.

 Some nerve cells can be comparatively smaller by 0.1

 The size of nerve cells is usually based on their functions

 They are found in the brain, spinal cord and peripheral

 For instance, the nerve cell, which transmits the electrical

A nerve cell is also known as a neuron. It is mainly involved in receiving and

A group of neurons forms a nerve and the nervous system.

A biological neuron has a cell body or soma to process the impulses,

Structure: The structure of artificial neural networks is inspired by biological

Human brain is slower than computer.

ReLU (Rectified Linear Unit) Function: It is the most popularly used

Sigmoid Function: It is by far the most commonly used activation function in

1. Binary Sigmoid Function

A binary sigmoid function is of the form:

A bipolar sigmoid function is of the form

The range of values of sigmoid functions can be varied depending on the

Hyperbolic Tangent Function: It is bipolar in nature. It is a widely

This function is similar to the bipolar sigmoid function.

You might also like