Scribd
Upload
29 views13 pages

Ann 1

Uploaded by

Siddhi Mhatre
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
29 views13 pages

Ann 1

Uploaded by

Siddhi Mhatre
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

What is ANN

Model??
▶ Artificial Neural Network(ANN) uses the processing of the brain as a
basis to develop algorithms that can be used to model complex
patterns and prediction problems.
▶ ANN is an empirical tool; its behaviour is analogous to the behaviour
of biological neural structures.
▶ ANN has the ability to identify underlying highly complex
relationships using input-output data.
Artificial Neural Networks

• The “building blocks” of neural networks are the neurons.


• In technical systems, we also refer to them as units or nodes.
• Basically, each neuron
⚫ receives input from many other neurons.
⚫ changes its internal state (activation) based on the current input.
⚫ sends one output signal to many other neurons, possibly including its
input neurons (recurrent network).
BIOLOGICAL NEURON MODEL
▶ Four parts of a typical nerve cell : -
1 DENDRITES: Accepts the inputs

2 SOMA: Process the


inputs
3 Axon: Turns the processed
inputs into
outputs.
4 Synapses: The electrochemical
contact between
the neurons.
ARTIFICIAL NUERON MODEL

▶ Inputs to the network are


represented by the mathematical
symbol, xn
▶ Each of these inputs are
multiplied by a connection weight
, wn

sum = w1 x1 + ……+ wn xn

▶ These products are simply


summed, fed through the transfer
function, f( ) to generate a result
and then output
TERMINOLOGY
Biological Terminology Artificial Neuron
Network Terminology
Neuron Node/Unit/Cell/Neurode

Synapse Connection/Edge/Link

Synaptic Efficiency Connection Strength/Weight

Firing Efficiency Node Output


How ANN Works?

Here I1, I2, I3 are Inputs


W1, W2, W3 are
Weights O is Output

Example Learning Procedure:


• Randomly assign weights (between 0-1
• Present inputs from training dat
• Get output O, nudge weights to gives
results toward our desired output
• Repeat; stop when no errors, or enough
epochs completed
Perception Training

wi (t 1)  wi (t)  wi wi= Weights Include Threshold


(t) T = Desired Output
wi (t)  (T  O)I i O = Actual Output
Example : T=0, O=1, W1=0.5, W2=0.3, I1=2, I2=1, θ=-
1

w1 (t  1)  0.5  (0  1)(2)  1.5


w2 (t  1)  0.3  (0  1)(1)  0.7
w (t  1)  1  (0  1)(1)  2

If we present this input again, we’d output 0 instead


LMS Learning
LMS = Least Mean Square learning Systems, more general than
the previous perceptron learning rule. The concept is to minimize
total error, as measured over all training examples, P. O is the
the
raw 
output, as calculated by  i wi

Ii 𝟏
𝟐
𝑫𝒊𝒔𝒕𝒂𝒏𝒄𝒆 (𝑳𝑴𝑺) = ∑ 𝑻 𝑷 − 𝑶𝑷
𝟐
𝑷

E.g. if we have two patterns and


T1=1, O1=0.8, T2=0, O2=0.5 then D=(0.5)[(1-0.8)2+(0-0.5)2]=.145

We want to minimize the LMS:


Back Propagation
⚫ Back-propagation is an example of supervised learning is used at each layer to
minimize the error between the layer’s response and the actual data.
⚫ The error at each hidden layer is an average of the evaluated error.
⚫ Hidden layer networks are trained this way
Back Propagation
▶ Very powerful - can learn any function, given enough hidden units!
With enough hidden units, we can generate any function.
▶ Have the same problems of Generalization vs. Memorization.
With too many units, we will tend to memorize the input and not
generalize well. Some schemes exist to “prune” the neural
network.
▶ Networks require extensive training, many parameters to fiddle
with. Can be extremely slow to train. May also fall into
local minima.
▶ Inherently parallel algorithm, ideal for multiprocessor
hardware.
▶ Despite the constraints, a very powerful algorithm that has seen
widespread successful deployment.
Number of neurons

▶ Many neurons:
 Higher accuracy
 Slower
 Risk of over‐fitting
 Memorizing, rather than understanding
 The network will be useless with new problems.

▶ Few neurons:
 Lower accuracy
 Inability to learn at all

▶ Optimal number.
Advantages and Disadvantages of
ANN
▶ Advantages. ▶ Disadvantages
 Adapt to unknown situations  Forgets
 Powerful, it can model complex  Not exact
functions.  Large complexity of the network
 Ease of use, learns by example, structure
and very little user domain specific  Hard to handle large no of data
expertise needed.  Slow Training.
 Fast Decision making
 Unpredictable Behaviour.
 It works generally good when there
are noisy and missing data.
Applications of ANN Model

▶ Pattern classification
 including patterns and sequences recognition, novelty detection and sequential
decision making.
⚫ (radar systems, face identification, handwritten text recognition)

▶ Prediction and financial analysis, and


▶ Control and Optimization.
▶ Time Series
▶ Data processing
 including filtering, clustering blinds source separation and compression.
⚫ (data mining, e-mail Spam filtering)

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy