neural network and genetic algorithm
up vote
-2
down vote
favorite
I am working with a complex system, the system has five variables - depending upon values of these five variables, the response of the system is measured. There are seven output variables that are measured in-order to completely define the response.
I have been using artificial neural network to model relationship between the five variables and the seven output parameters. This has been successful so far.. The ANNs can predict really well the output (I have tested the trained network on a validation set of testcases also). I used python Keras/tensor flow for the same.
BTW, I also tried the linear regression as function approximator but it produces large errors. These errors are expected considering that the system is highly non-linear and may not be continuous everywhere.
Now, I would like to predict the values of the five variables from a vector of the seven output parameters (target vector). Tried using Genetic algorithm for the same. After a lot of effort in designing the GA, I still end up getting high differences between target vector and the GA prediction. I just try to minimize the mean squared error between ANN prediction (function approximator) and target vector.
Is this the right approach to use ANN as function approximator and GA for design space exploration?
python neural-network genetic-algorithm
asked Nov 13 at 7:12
Puneeth
61
|
show 1 more comment
up vote
-2
down vote
favorite
I am working with a complex system, the system has five variables - depending upon values of these five variables, the response of the system is measured. There are seven output variables that are measured in-order to completely define the response.
I have been using artificial neural network to model relationship between the five variables and the seven output parameters. This has been successful so far.. The ANNs can predict really well the output (I have tested the trained network on a validation set of testcases also). I used python Keras/tensor flow for the same.
BTW, I also tried the linear regression as function approximator but it produces large errors. These errors are expected considering that the system is highly non-linear and may not be continuous everywhere.
Now, I would like to predict the values of the five variables from a vector of the seven output parameters (target vector). Tried using Genetic algorithm for the same. After a lot of effort in designing the GA, I still end up getting high differences between target vector and the GA prediction. I just try to minimize the mean squared error between ANN prediction (function approximator) and target vector.
Is this the right approach to use ANN as function approximator and GA for design space exploration?
python neural-network genetic-algorithm
asked Nov 13 at 7:12
Puneeth
61
4
What is your objective? Also GA cannot do prediction, it is used for optimization. May be u can find the best combination of five variables which can give the max value in your target variable using GA
– AILearning
Nov 13 at 7:22
" May be u can find the best combination of five variables which can give the max value in your target variable using GA –" I am doing this but slightly in a different way. I would like to minimize the error between the target and the predicted variables. The ANN serves as the function approximator. But, this does not seem to work. I now started thinking if GA can be used or not when the target function is ANN.
– Puneeth
Nov 13 at 7:50
GA is not an approach for function appropriator. What do you mean by "this does not work". But you mentioned earlier as "The ANNs can predict really well the output"
– AILearning
Nov 13 at 8:24
Input data ----> ANN ----> output data : ANN is used to build a relationship between input and output. How to find a set of "input variables" that can produce a specific output "target"? I used GA for this. target -----> GA -------> input variables What do I optimize in GA? it is the mean squared error of ANN output and target. So, how does it work? GA sets an initial population, sends those values to ANN, ANN predicts the output - GA compares ANN output with target - finds mse - repeats until a minimum mse is reached. Hence, GA is used as optimizer and not as function appropriator.
– Puneeth
Nov 13 at 8:35
Is this the right approach to use ANN as function approximator and GA for design space exploration? - Yes. I am not getting, where the issues is now!
– AILearning
Nov 13 at 8:39
|
show 1 more comment
up vote
-2
down vote
favorite
up vote
-2
down vote
favorite
I am working with a complex system, the system has five variables - depending upon values of these five variables, the response of the system is measured. There are seven output variables that are measured in-order to completely define the response.
I have been using artificial neural network to model relationship between the five variables and the seven output parameters. This has been successful so far.. The ANNs can predict really well the output (I have tested the trained network on a validation set of testcases also). I used python Keras/tensor flow for the same.
BTW, I also tried the linear regression as function approximator but it produces large errors. These errors are expected considering that the system is highly non-linear and may not be continuous everywhere.
Now, I would like to predict the values of the five variables from a vector of the seven output parameters (target vector). Tried using Genetic algorithm for the same. After a lot of effort in designing the GA, I still end up getting high differences between target vector and the GA prediction. I just try to minimize the mean squared error between ANN prediction (function approximator) and target vector.
Is this the right approach to use ANN as function approximator and GA for design space exploration?
python neural-network genetic-algorithm
asked Nov 13 at 7:12
Puneeth
61
I am working with a complex system, the system has five variables - depending upon values of these five variables, the response of the system is measured. There are seven output variables that are measured in-order to completely define the response.
I have been using artificial neural network to model relationship between the five variables and the seven output parameters. This has been successful so far.. The ANNs can predict really well the output (I have tested the trained network on a validation set of testcases also). I used python Keras/tensor flow for the same.
BTW, I also tried the linear regression as function approximator but it produces large errors. These errors are expected considering that the system is highly non-linear and may not be continuous everywhere.
Now, I would like to predict the values of the five variables from a vector of the seven output parameters (target vector). Tried using Genetic algorithm for the same. After a lot of effort in designing the GA, I still end up getting high differences between target vector and the GA prediction. I just try to minimize the mean squared error between ANN prediction (function approximator) and target vector.
Is this the right approach to use ANN as function approximator and GA for design space exploration?
python neural-network genetic-algorithm
python neural-network genetic-algorithm
asked Nov 13 at 7:12
Puneeth
61
asked Nov 13 at 7:12
Puneeth
61
asked Nov 13 at 7:12
Puneeth
61
asked Nov 13 at 7:12
Puneeth
61
asked Nov 13 at 7:12
Puneeth
61
61
4
What is your objective? Also GA cannot do prediction, it is used for optimization. May be u can find the best combination of five variables which can give the max value in your target variable using GA
– AILearning
Nov 13 at 7:22
" May be u can find the best combination of five variables which can give the max value in your target variable using GA –" I am doing this but slightly in a different way. I would like to minimize the error between the target and the predicted variables. The ANN serves as the function approximator. But, this does not seem to work. I now started thinking if GA can be used or not when the target function is ANN.
– Puneeth
Nov 13 at 7:50
GA is not an approach for function appropriator. What do you mean by "this does not work". But you mentioned earlier as "The ANNs can predict really well the output"
– AILearning
Nov 13 at 8:24
Input data ----> ANN ----> output data : ANN is used to build a relationship between input and output. How to find a set of "input variables" that can produce a specific output "target"? I used GA for this. target -----> GA -------> input variables What do I optimize in GA? it is the mean squared error of ANN output and target. So, how does it work? GA sets an initial population, sends those values to ANN, ANN predicts the output - GA compares ANN output with target - finds mse - repeats until a minimum mse is reached. Hence, GA is used as optimizer and not as function appropriator.
– Puneeth
Nov 13 at 8:35
Is this the right approach to use ANN as function approximator and GA for design space exploration? - Yes. I am not getting, where the issues is now!
– AILearning
Nov 13 at 8:39
|
show 1 more comment
4
What is your objective? Also GA cannot do prediction, it is used for optimization. May be u can find the best combination of five variables which can give the max value in your target variable using GA
– AILearning
Nov 13 at 7:22
" May be u can find the best combination of five variables which can give the max value in your target variable using GA –" I am doing this but slightly in a different way. I would like to minimize the error between the target and the predicted variables. The ANN serves as the function approximator. But, this does not seem to work. I now started thinking if GA can be used or not when the target function is ANN.
– Puneeth
Nov 13 at 7:50
GA is not an approach for function appropriator. What do you mean by "this does not work". But you mentioned earlier as "The ANNs can predict really well the output"
– AILearning
Nov 13 at 8:24
Input data ----> ANN ----> output data : ANN is used to build a relationship between input and output. How to find a set of "input variables" that can produce a specific output "target"? I used GA for this. target -----> GA -------> input variables What do I optimize in GA? it is the mean squared error of ANN output and target. So, how does it work? GA sets an initial population, sends those values to ANN, ANN predicts the output - GA compares ANN output with target - finds mse - repeats until a minimum mse is reached. Hence, GA is used as optimizer and not as function appropriator.
– Puneeth
Nov 13 at 8:35
Is this the right approach to use ANN as function approximator and GA for design space exploration? - Yes. I am not getting, where the issues is now!
– AILearning
Nov 13 at 8:39
4
4
What is your objective? Also GA cannot do prediction, it is used for optimization. May be u can find the best combination of five variables which can give the max value in your target variable using GA
– AILearning
Nov 13 at 7:22
What is your objective? Also GA cannot do prediction, it is used for optimization. May be u can find the best combination of five variables which can give the max value in your target variable using GA
– AILearning
Nov 13 at 7:22
" May be u can find the best combination of five variables which can give the max value in your target variable using GA –" I am doing this but slightly in a different way. I would like to minimize the error between the target and the predicted variables. The ANN serves as the function approximator. But, this does not seem to work. I now started thinking if GA can be used or not when the target function is ANN.
– Puneeth
Nov 13 at 7:50
" May be u can find the best combination of five variables which can give the max value in your target variable using GA –" I am doing this but slightly in a different way. I would like to minimize the error between the target and the predicted variables. The ANN serves as the function approximator. But, this does not seem to work. I now started thinking if GA can be used or not when the target function is ANN.
– Puneeth
Nov 13 at 7:50
GA is not an approach for function appropriator. What do you mean by "this does not work". But you mentioned earlier as "The ANNs can predict really well the output"
– AILearning
Nov 13 at 8:24
GA is not an approach for function appropriator. What do you mean by "this does not work". But you mentioned earlier as "The ANNs can predict really well the output"
– AILearning
Nov 13 at 8:24
Input data ----> ANN ----> output data : ANN is used to build a relationship between input and output. How to find a set of "input variables" that can produce a specific output "target"? I used GA for this. target -----> GA -------> input variables What do I optimize in GA? it is the mean squared error of ANN output and target. So, how does it work? GA sets an initial population, sends those values to ANN, ANN predicts the output - GA compares ANN output with target - finds mse - repeats until a minimum mse is reached. Hence, GA is used as optimizer and not as function appropriator.
– Puneeth
Nov 13 at 8:35
Input data ----> ANN ----> output data : ANN is used to build a relationship between input and output. How to find a set of "input variables" that can produce a specific output "target"? I used GA for this. target -----> GA -------> input variables What do I optimize in GA? it is the mean squared error of ANN output and target. So, how does it work? GA sets an initial population, sends those values to ANN, ANN predicts the output - GA compares ANN output with target - finds mse - repeats until a minimum mse is reached. Hence, GA is used as optimizer and not as function appropriator.
– Puneeth
Nov 13 at 8:35
Is this the right approach to use ANN as function approximator and GA for design space exploration? - Yes. I am not getting, where the issues is now!
– AILearning
Nov 13 at 8:39
Is this the right approach to use ANN as function approximator and GA for design space exploration? - Yes. I am not getting, where the issues is now!
– AILearning
Nov 13 at 8:39
|
show 1 more comment
1 Answer
1
active
oldest
votes
up vote
0
down vote
accepted
Yes, it is a good approach to do search space exploration using GA. But designing the crossover, mutation, generation evolution logic, etc. plays a major role in the determining the performance of the Genetic algo.
If your search space is limited, you can use exact methods (which solves to optimality).
There are few implementation in python-scipy itself
If you prefer to go with meta-heuristics,
there is a wide range of options other than Genetic algorithm
Memetic algorithm
Tabu Search
Simulated annealing
Particle swarm optimization
Ant colony optimization
answered Nov 13 at 8:52
AILearning
461417
1
thank you for the answer.
– Puneeth
Nov 13 at 9:10
add a comment |
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
up vote
0
down vote
accepted
Yes, it is a good approach to do search space exploration using GA. But designing the crossover, mutation, generation evolution logic, etc. plays a major role in the determining the performance of the Genetic algo.
If your search space is limited, you can use exact methods (which solves to optimality).
There are few implementation in python-scipy itself
If you prefer to go with meta-heuristics,
there is a wide range of options other than Genetic algorithm
Memetic algorithm
Tabu Search
Simulated annealing
Particle swarm optimization
Ant colony optimization
answered Nov 13 at 8:52
AILearning
461417
1
thank you for the answer.
– Puneeth
Nov 13 at 9:10
add a comment |
up vote
0
down vote
accepted
Yes, it is a good approach to do search space exploration using GA. But designing the crossover, mutation, generation evolution logic, etc. plays a major role in the determining the performance of the Genetic algo.
If your search space is limited, you can use exact methods (which solves to optimality).
There are few implementation in python-scipy itself
If you prefer to go with meta-heuristics,
there is a wide range of options other than Genetic algorithm
Memetic algorithm
Tabu Search
Simulated annealing
Particle swarm optimization
Ant colony optimization
answered Nov 13 at 8:52
AILearning
461417
1
thank you for the answer.
– Puneeth
Nov 13 at 9:10
add a comment |
up vote
0
down vote
accepted
up vote
0
down vote
accepted
Yes, it is a good approach to do search space exploration using GA. But designing the crossover, mutation, generation evolution logic, etc. plays a major role in the determining the performance of the Genetic algo.
If your search space is limited, you can use exact methods (which solves to optimality).
There are few implementation in python-scipy itself
If you prefer to go with meta-heuristics,
there is a wide range of options other than Genetic algorithm
Memetic algorithm
Tabu Search
Simulated annealing
Particle swarm optimization
Ant colony optimization
answered Nov 13 at 8:52
AILearning
461417
Yes, it is a good approach to do search space exploration using GA. But designing the crossover, mutation, generation evolution logic, etc. plays a major role in the determining the performance of the Genetic algo.
If your search space is limited, you can use exact methods (which solves to optimality).
There are few implementation in python-scipy itself
If you prefer to go with meta-heuristics,
there is a wide range of options other than Genetic algorithm
Memetic algorithm
Tabu Search
Simulated annealing
Particle swarm optimization
Ant colony optimization
answered Nov 13 at 8:52
AILearning
461417
answered Nov 13 at 8:52
AILearning
461417
answered Nov 13 at 8:52
AILearning
461417
answered Nov 13 at 8:52
AILearning
461417
461417
1
thank you for the answer.
– Puneeth
Nov 13 at 9:10
add a comment |
1
thank you for the answer.
– Puneeth
Nov 13 at 9:10
1
1
thank you for the answer.
– Puneeth
Nov 13 at 9:10
thank you for the answer.
– Puneeth
Nov 13 at 9:10
add a comment |
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53275666%2fneural-network-and-genetic-algorithm%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
4
What is your objective? Also GA cannot do prediction, it is used for optimization. May be u can find the best combination of five variables which can give the max value in your target variable using GA
– AILearning
Nov 13 at 7:22
" May be u can find the best combination of five variables which can give the max value in your target variable using GA –" I am doing this but slightly in a different way. I would like to minimize the error between the target and the predicted variables. The ANN serves as the function approximator. But, this does not seem to work. I now started thinking if GA can be used or not when the target function is ANN.
– Puneeth
Nov 13 at 7:50
GA is not an approach for function appropriator. What do you mean by "this does not work". But you mentioned earlier as "The ANNs can predict really well the output"
– AILearning
Nov 13 at 8:24
Input data ----> ANN ----> output data : ANN is used to build a relationship between input and output. How to find a set of "input variables" that can produce a specific output "target"? I used GA for this. target -----> GA -------> input variables What do I optimize in GA? it is the mean squared error of ANN output and target. So, how does it work? GA sets an initial population, sends those values to ANN, ANN predicts the output - GA compares ANN output with target - finds mse - repeats until a minimum mse is reached. Hence, GA is used as optimizer and not as function appropriator.
– Puneeth
Nov 13 at 8:35
Is this the right approach to use ANN as function approximator and GA for design space exploration? - Yes. I am not getting, where the issues is now!
– AILearning
Nov 13 at 8:39