neural net 3rdclass
TRANSCRIPT
-
7/29/2019 Neural Net 3rdClass
1/35
A Brief Overview of Neural
Networks
-
7/29/2019 Neural Net 3rdClass
2/35
Relation to Biolo ical Brain: Biolo ical Neural Network
The Artificial Neuron Types of Networks and Learning Techniques
Supervised Learning & Backpropagation Training
Algorithm
Applications
-
7/29/2019 Neural Net 3rdClass
3/35
-
7/29/2019 Neural Net 3rdClass
4/35
WINeuron
f(n) OutputsPU
W ActivationTS
= e g
-
7/29/2019 Neural Net 3rdClass
5/35
1
Output
: ( )1
nSIGMOID f ne= +
Input
LI EAR n n=
-
7/29/2019 Neural Net 3rdClass
6/35
Multiple Inputs and Multiple Inputs
and layers
-
7/29/2019 Neural Net 3rdClass
7/35
.Feedback
Recurrent Networks
-
7/29/2019 Neural Net 3rdClass
8/35
Recurrent Networks
Feed forward networks:
One input pattern produces one output
Recurrency
Nodes connect back to other nodes orthemselves
Information flow is multidirectional
Sense of time and memory of previous state(s)
o og ca nervous sys ems s ow g eve s o
recurrency (but feed-forward structures exists too)
-
7/29/2019 Neural Net 3rdClass
9/35
components of biological neural nets:
1. Neurones (nodes)
2. Synapses (weights)
-
7/29/2019 Neural Net 3rdClass
10/35
-
Information flow is unidirectional
Data is resented to In ut la er
Passed on to Hidden Layer
Passed on to Output layer
Information is distributed
-
7/29/2019 Neural Net 3rdClass
11/35
Neural networks are ood for rediction roblems.
The in uts are well understood. You have a
good idea of which features of the data areimportant, but not necessarily how to combine.
The output is well understood. You know what.
Experience is available. You have plenty ofexamples where both the inputs and the output
are known. This experience will be used to trainthe network.
-
7/29/2019 Neural Net 3rdClass
12/35
(1 0.25) + (0.5 (-1.5)) = 0.25 + (-0.75) = - 0.5
0.3775
1 5.0=
+ e
Squashing:
-
7/29/2019 Neural Net 3rdClass
13/35
Inputs from theActual S stem
ExpectedOutput
+Actual
Neural Network
-
Training
Error
-
7/29/2019 Neural Net 3rdClass
14/35
Inputs First Hiddenlayer
SecondHidden Layer
Layer
-
7/29/2019 Neural Net 3rdClass
15/35
Signal Flow
Backpropagation of Errors
Function Signals
Error Signals
-
7/29/2019 Neural Net 3rdClass
16/35
Neural networks for Directed Data Mining: Building
a mo e or c ass ca on an pre c on
1. Identify the input and output features
.
range is between 0 and 1.3. Set up a network on a representative set of training
examp es.
4. Train the network on a representative set of training
exam les.
5. Test the network on a test set strictly independent fromthe training examples. If necessary repeat the training,
, ,parameters. Evaluate the network using the evaluationset to see how well it performs.
.outcomes for unknown inputs.
-
7/29/2019 Neural Net 3rdClass
17/35
= F(n)= 1/(1+exp(-n)), where n is the net input tothe neuron.
Derivative= F(n) = (output of the neuron)(1-
output of the neuron) : Slope of the transferfunction.
Output layer transfer function: Linear function=
n =n; utput= nput to t e neuronDerivative= F(n)= 1
-
7/29/2019 Neural Net 3rdClass
18/35
Purpose of the
Activation Function We want the unit to be active near +1 when the ri ht
inputs are given We want the unit to be inactive (near 0) when the
wrong npu s are g ven.
Its preferable for activation function to be nonlinear.
Otherwise the entire neural network colla ses into a
simple linear function.
-
7/29/2019 Neural Net 3rdClass
19/35
function
Step function Sign function Sigmoid (logistic) function
step(x) = 1, ifx > threshold0, if x threshold
in icture above, threshold = 0
sign(x) = +1, if x > 0
-1, if x 0
sigmoid(x) = 1/(1+e-x)
Adding an extra input with activation a0 = - 1 and weight=0,j
threshold at t. This way we can always assume a 0 threshold.
-
7/29/2019 Neural Net 3rdClass
20/35
s ng a as e g t to
-1
x1
W1
x2
W2
W1x1+ W2x2 < T
W1x1+ W2x2 - T < 0
-
7/29/2019 Neural Net 3rdClass
21/35
errors using gradient descent training.
Red: Current weights range: p a e we g s
Black boxes: Inputs and outputs to a neuron
Blue: Sensitivities at each layer
-
7/29/2019 Neural Net 3rdClass
22/35
The perceptron learning rule performs gradient descentin
weight space. Error surface: The surface that describes the error on
each example as a function of all the weights in the. .
(It could also be called a state in the state space ofpossible weights, i.e., weight space.)
respect to each weight (i.e., the gradient -- how much theerror would change if we made a small change in each
weight). Then the weights are being altered in an amountpropor ona o e s ope n eac rec on correspon ngto a weight). Thus the network as a whole is moving inthe direction of steepest descent on the error surface.
-
7/29/2019 Neural Net 3rdClass
23/35
Definition ofError:
This is introduced to simplify the math on the next slide
22
2
)(
2
ErrotE
examples
==
Here,t is the correct (desired) output ando is the actual
ou pu o e neura ne .
-
7/29/2019 Neural Net 3rdClass
24/35
Reduction of Squared Error
the partial derivative of E with respect to each weight:
Err
E is
n
jj Wrr
W
=
= c a n ru e or er va ves
This is called in
a vector
j
k
kk
j
xingErr
W
=
=
)('
0
expan secon rr a ove to t g n
0=
W
tbecause and chain rule
jjj xingErrWW + )('
The weight is updated by times this gradient of error E in weight space. The factthat the weight is updated in the correct direction (+/-) can be verified with examples.
The learning rate, , is typically set to a small value such as 0.1
-
7/29/2019 Neural Net 3rdClass
25/35
G2= (0.6508)(1-G1= (0.6225)(1-
0.62250.6225 0.6508
. . . = .. . . = .
0.5
0.5
0.5.
0.51
.0.6508
0.50.5
0.50.5 0.62250.6225
0.6508
0.6508
G3=(1)(0.3492)=0.3492Gradient of the neuron= G=slope of the transfer
function[{(weight of the
Gradient of the outputneuron = slope of the
transfer function error
Error=1-0.6508=0.3492neuron to t e next neuron
(output of the neuron)}]
-
7/29/2019 Neural Net 3rdClass
26/35
New Weight=Old Weight + {(learning rate)(gradient)(prior output)}
0.5+(0.5)(0.3492)(0.6508)0.5+(0.5)(0.0397)(0.6225)0.5+(0.5)(0.0093)(1)
0.6136
0.5124 0.5124
.
0.5047
0.51240.61360.5047
-
7/29/2019 Neural Net 3rdClass
27/35
G2= (0.6545)(1-G1= (0.6236)(1-
0.63910.62360.6545
. . . = .. . . = .
0.5047
0.5124
0.6136.
0.51241
.0.8033
0.61360.5047
0.51240.5047
0.63910.6236
0.8033
0.6545G3=(1)(0.1967)=0.1967
Error=1-0.8033=0.1967
-
7/29/2019 Neural Net 3rdClass
28/35
New Weight=Old Weight + {(learning rate)(gradient)(prior output)}
0.6136+(0.5)(0.1967)(0.6545)0.5124+(0.5)(0.0273)(0.6236)0.5047+(0.5)(0.0066)(1)
0.6779
0.5209 0.5209
.
0.508
0.52090.67790.508
-
7/29/2019 Neural Net 3rdClass
29/35
0.65040.62430.6571
0.508
0.5209
0.6779.
0.52091
.0.8909
0.67790.508
0.52090.508
0.65040.6243
0.89090.6571
-
7/29/2019 Neural Net 3rdClass
30/35
Output Expected ErrorWeights
w w w
Initial conditions 0.5 0.5 0.5 0.6508 1 0.3492
. . . . .
Pass 2 Update 0.508 0.5209 0.6779 0.8909 1 0.1091
W1: Weights from the input to the input layerW2: Weights from the input layer to the hidden layer
W3: Weights from the hidden layer to the output layer
-
7/29/2019 Neural Net 3rdClass
31/35
backpropagation continues until the
reached.
-
Other complicated backpropagation
ra n ng a gor ms a so ava a e.
-
7/29/2019 Neural Net 3rdClass
32/35
O1
W1O3 = 1/[1+exp(-N)]
Output 1
O2W2 N =
(O1W1)
Error =Actual
O = Output of the neuron
W = Weight
N = Net input to the neuron
+(O2W
2)
0Input
To reduce error: Change in weights:
o Learning rate
Gradient: rate of change of error w.r.t rate of change of N Prior output (O1 and O2)
-
7/29/2019 Neural Net 3rdClass
33/35
Gradient : Rate of change of error w.r.t rate of change in net input to
o For output neurons Slope of the transfer function error
o For hidden neurons : A bit complicated ! : error fed back in terms of
gradient of successive neurons
Slope of the transfer function [ (gradient of next neuron
weight connecting the neuron to the next neuron)]
Why summation? Share the responsibility!!
-
7/29/2019 Neural Net 3rdClass
34/35
G1=0.66(1-0.66)(0.34)= 0.0763
1 0.731
0.5
0.6645 0.66 1
Error = 1-0.66 = 0.34
0.4
0.50.5
0.598 0.5 0.66450.66 0
Error = 0-0.66 = -0.66
G1=0.66(1-0.66)(-0.66)= -0.148Reduce more
Increase less
-
7/29/2019 Neural Net 3rdClass
35/35
number of neurons in each layer..
Changing the learning rate. Training for longer times.
T e of re- rocessin and ost-
processing.