What is competitive learning? How does it differ from Hebbian learning?
Competitive Learning is a type of unsupervised learning used in neural networks and machine learning. In competitive learning, a set of neurons or processing units competes to respond to a given input. The neuron that most closely matches the input wins the competition and gets activated. Competitive learning is often used for clustering and feature extraction.
________ __________ ______ _____ _____ __________._______ __________ ______ ________ ________ _________.
_______ ____ ___ ________ ______ _______.
_____ ____ __________ _______ ____ ________ _____ _______ ______.
_____ ______ __________ ____ ___.
_____ ______ _____ ____ ____ _________.
______ _________ ____ ________ _____ ____ ____ ________ _________ _______ ____.
________ ________ ________ ______ __________ ________.
_______ _____ ___ _____ _______ ________ ____ ___.
__________ _____ _________ _____ __________ _______ _________ __________ ____ _______ ______.
_________ __________ ___ ___ _________ _____ __________ _________ ________.
___ _____ _______ _______ ________ ___ ______ __________.
_______ ____ ________ _______ __________ ___ ______ ________ _______ ____ _____ ________.
___ __________ _______ ____ ____ ______ ___ _______ __________.
___ _______ ____ ______ _________ ___ ____.
_____ ________ _________ _____ ____ _________ ______ __________ ______.
___ ________ ______ ________ ___.
_________ _________ ____ ___ _______ ________ __________.
___ ___ ___ _________ ________ _________ ___ _______ _________ __________.
__________ _____ ________ ___ _______.
__________ ___ ______ ____ ___.
________ _____ _____ __________ _______ _____ _______ __________ ____.
______ ___ ___ __________ _____ __________ _______ ____ ________ _________ ___ _____.
_________ _____ __________ _______ ________ _____ _________ ___ _______ _____ ________ ___.
_______ ___ ___ ______ _______.
_________ __________ __________ ____ ____.
____ _________ ________ _______ ______ ________ __________ _______ _____ __________ _______.
__________ _________ _______ _______ __________ _____ _________ ______ _________.
_________ _______ ________ _______.
Get Full Answer on WhatsApp
Two sensors based upon their detection levels and gain settings are compared. The following table of gain settings and sensor detection levels with a standard item being monitored provides typical membership values to represent the detection levels for each of the sensors.
| Gain Setting | Sensor 1 detection levels | Sensor 2 detection levels |
| 0 | 0 | 0 |
| 20 | 0.5 | 0.35 |
| 40 | 0.65 | 0.5 |
| 60 | 0.85 | 0.75 |
| 80 | 1 | 0.90 |
| 100 | 1 | 1 |
Find max-average composition for R ( x , y ) and S ( x , y ) defined by the following relational matrices:
Maximize f ( x , y ) = 8 x + 6 y
Subject to 2x + 3y 6
-3x + 2y 3
2x + y 4
0 x
2
Using genetic algorithm
Use a binary-coded Genetic algorithm (GA) to minimize the function f ( x1 , x2 ) = x1+ x2 + 2x12- x22+ x1 , x2, in the range of 0 x1, x2
5 . Use a random population of size N = 6 , a single point crossover with probability Pc=1 and neglect mutation. Assume 3 bits for each variable and thus the GA-string will be 6- bits long. Show only one iteration by hand calculation.
For these two fuzzy sets find the union, intersection, complement of difference
- C , and verify any one of Demorgan’s law.
i) graphically and
ii) numerically
Write any three terminating conditions used in learning of a neural network.
Let an activation function be defined as , . Show that
What is the value of
( v ) at the origin? Also, find the value of
as v approaches +
and -
.