Scribd
Upload
28 views

M. Raihan

This document discusses neural networks and the biological inspiration behind them. It describes how neurons function in the brain, receiving and sending electrical signals via dendrites, the cell body, and the axon. Early neural network models like McCulloch and Pitts neurons simplified real neurons into units that sum their weighted inputs and fire an output if the threshold is reached. The document outlines some of the topics that will be covered in a 3 credit hour course on neural networks, including biologically inspired concepts, threshold output firing, and limitations of early neural models.

Uploaded by

Sabuj Dhali
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
28 views

M. Raihan

This document discusses neural networks and the biological inspiration behind them. It describes how neurons function in the brain, receiving and sending electrical signals via dendrites, the cell body, and the axon. Early neural network models like McCulloch and Pitts neurons simplified real neurons into units that sum their weighted inputs and fire an output if the threshold is reached. The document outlines some of the topics that will be covered in a 3 credit hour course on neural networks, including biologically inspired concepts, threshold output firing, and limitations of early neural models.

Uploaded by

Sabuj Dhali
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 18

M.

Raihan
Email: [email protected]
Neural Networks
Neural Networks

18-Sep-17 3
Neural Networks
We are born with about 100 billion
neurons
A neuron may connect to as many as
100,000 other neurons

18-Sep-17 4
Human Brain

18-Sep-17 5
What is Neuron
Neurons are the fundamental units of the brain
and nervous system.
The cells responsible for receiving sensory input
from the external world
For sending motor commands to our muscles
For transforming and relaying the electrical
signals at every step in between.

18-Sep-17 6
How does a Neuron look like
A useful analogy is to think of a neuron as a tree.
A neuron has three main parts: dendrites, an axon, and a cell body or soma
which can be represented as the branches, roots and trunk of a tree
respectively.
A dendrite (tree branch) is where a neuron receives input from other cells.
The axon (tree roots) is the output structure of the neuron; when a neuron
wants to talk to another neuron, it sends an electrical message called an
action potential throughout the entire axon.
The soma (tree trunk) is where the nucleus lies, where the neuron’s DNA is
housed, and where proteins are made to be transported throughout the
axon and dendrites.
18-Sep-17 7
Continue

18-Sep-17 8
Inspiration from Neurobiology
A neuron: many-inputs / one output unit.
Output can be excited or not excited.
Incoming signals from other neurons
determine if the neuron shall excite ("fire")
Output subject to attenuation in the
synapses, which are junction parts of the
neuron
18-Sep-17 9
Hebb’s Rule
If an input of a neuron is repeatedly and
persistently causing the neuron to fire, a
metabolic change happens in the synapse
of that particular input to reduce its
resistance.

18-Sep-17 10
McCulloch and Pitts Neurons
McCulloch & Pitts (1943) are generally
recognized as the designers of the first neural
network.
Many of their ideas still used today (e.g.
many simple units combine to give increased
computational power and the idea of a
threshold).
18-Sep-17 11
McCulloch and Pitts Neurons
Greatly simplified biological neurons
Sum the inputs
If total is less than some threshold, neuron fires
Otherwise does not

18-Sep-17 12
McCulloch and Pitts Neurons
The weight wj can be positive or negative
Inhibitory or excitatory.

Use only a linear sum of inputs.


No refractory period.
Use a simple output instead of a pulse (spike train)

18-Sep-17 13
Biologically Inspired
Electro-chemical signals.
Threshold output firing.

18-Sep-17 14
The Perceptron
Binary classifier functions.
Threshold activation function.

18-Sep-17 15
Limitations of
(McCulloch and Pitts Neurons Model)

18-Sep-17 16
Course Curriculum
Credit Hour : 03
3 class test will be taken.

18-Sep-17 17
Thank You

18-Sep-17 18

You might also like