Basic Neural Network
- Sunny Chandra
©c17hawke
©c17hawke
INPUT
ARCHITECTURE OF SINGLE NEURON
input c
input a
input b
©c17hawke
AN EXAMPLE OF ACTIVATION FUNCTION
©c17hawke
1
2
3
1
2
3
1
2
3
INPUT
OUTPUT
Input layer ( buffer layer )
©c17hawke
1
2
3
1
2
3
1
2
3
INPUT
OUTPUT
THIS CAN BE AN EXAMPLE OF CLASSIFICATION NN WITH 3 DIFFERENT CLASS
©c17hawke
1
2
3
1
2
3
1
INPUT
OUTPUT
REGRESSION NN EXAMPLE
©c17hawke
1
2
1
2
©c17hawke
=
=
=
=
*
©c17hawke
=
=
=
=
*
W
©c17hawke
=
=
=
=
*
W
I
©c17hawke
=
=
=
=
*
W
I
Z
©c17hawke
=
=
=
=
*
W
I
Z
act(Z)
©c17hawke
=
=
=
=
*
W
I
Z
act(Z)
©c17hawke
=
=
=
*
W
I
Z
act(Z)
©c17hawke
1
2
1
2
predicted val
actual val
error
ERROR CALCULATION
©c17hawke
1
2
1
error
ERROR CALCULATION
= 3.0
= 1.0
Can we do this ??
Correct approach
©c17hawke