Multilayer Perceptron questions
up vote
0
down vote
favorite
I am working on a school project, designing a neural network (mlp),
I made it with a GUI so it can be interactive.
For all my neurons I am using SUM as GIN function,
the user can select the activation function for each layer.
I have a theoretical question:
- do I set the threshold,g and a - parameters individually for each neuron or for the entire layer?
neural-network perceptron
asked 2 days ago
random_numbers
104
add a comment |
up vote
0
down vote
favorite
I am working on a school project, designing a neural network (mlp),
I made it with a GUI so it can be interactive.
For all my neurons I am using SUM as GIN function,
the user can select the activation function for each layer.
I have a theoretical question:
- do I set the threshold,g and a - parameters individually for each neuron or for the entire layer?
neural-network perceptron
asked 2 days ago
random_numbers
104
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I am working on a school project, designing a neural network (mlp),
I made it with a GUI so it can be interactive.
For all my neurons I am using SUM as GIN function,
the user can select the activation function for each layer.
I have a theoretical question:
- do I set the threshold,g and a - parameters individually for each neuron or for the entire layer?
neural-network perceptron
asked 2 days ago
random_numbers
104
I am working on a school project, designing a neural network (mlp),
I made it with a GUI so it can be interactive.
For all my neurons I am using SUM as GIN function,
the user can select the activation function for each layer.
I have a theoretical question:
- do I set the threshold,g and a - parameters individually for each neuron or for the entire layer?
neural-network perceptron
neural-network perceptron
asked 2 days ago
random_numbers
104
asked 2 days ago
random_numbers
104
edited 2 days ago
asked 2 days ago
random_numbers
104
asked 2 days ago
random_numbers
104
asked 2 days ago
random_numbers
104
104
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
up vote
0
down vote
accepted
Looks nice ! You can have 3 hidden layers, but you'll see with experimenting, you will rarely need that many layers. What is your training pattern ?
Answer to your question depends on your training pattern and purpose of input neurons.. when e.g. some input neuron has a different type of value, you could use another threshold function or different settings for parameters in neurons connected to that input neuron.
But in general, it is better to feed neural network input into seperate perceptrons. So, the answer is: in theory, you could preset individual properties of neurons.. but in practice of back-propagation learning, it is not needed. There are no "individual properties" of neurons, the weight values that result of your training cycles will differ every time. All initial weights can be set on a small random value, transfer threshold and learning rate are to be set per layer.
answered 2 days ago
Goodies
35416
We haven`t learned yet about learning patterns , ohh wait we did , supervised learning, this project is more of a GUI thing and so the teacher can see that we understand how a neural network should work, In a later project we will have to implement a network to solve a problem. And we will only be learning about feed forward, no back propagation.
– random_numbers
2 days ago
In that case I would keep it simple. User should specify the number of layers, the size of layers and a maximum random initial weight value for all weights. Use a single treshold function for all neurons.. There is one thing: you will need to set 3 learning rates in above case: when using hidden layers, user should be able to set different learning rates for each layer.
– Goodies
2 days ago
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
Looks nice ! You can have 3 hidden layers, but you'll see with experimenting, you will rarely need that many layers. What is your training pattern ?
Answer to your question depends on your training pattern and purpose of input neurons.. when e.g. some input neuron has a different type of value, you could use another threshold function or different settings for parameters in neurons connected to that input neuron.
But in general, it is better to feed neural network input into seperate perceptrons. So, the answer is: in theory, you could preset individual properties of neurons.. but in practice of back-propagation learning, it is not needed. There are no "individual properties" of neurons, the weight values that result of your training cycles will differ every time. All initial weights can be set on a small random value, transfer threshold and learning rate are to be set per layer.
answered 2 days ago
Goodies
35416
We haven`t learned yet about learning patterns , ohh wait we did , supervised learning, this project is more of a GUI thing and so the teacher can see that we understand how a neural network should work, In a later project we will have to implement a network to solve a problem. And we will only be learning about feed forward, no back propagation.
– random_numbers
2 days ago
In that case I would keep it simple. User should specify the number of layers, the size of layers and a maximum random initial weight value for all weights. Use a single treshold function for all neurons.. There is one thing: you will need to set 3 learning rates in above case: when using hidden layers, user should be able to set different learning rates for each layer.
– Goodies
2 days ago
add a comment |
up vote
0
down vote
accepted
Looks nice ! You can have 3 hidden layers, but you'll see with experimenting, you will rarely need that many layers. What is your training pattern ?
Answer to your question depends on your training pattern and purpose of input neurons.. when e.g. some input neuron has a different type of value, you could use another threshold function or different settings for parameters in neurons connected to that input neuron.
But in general, it is better to feed neural network input into seperate perceptrons. So, the answer is: in theory, you could preset individual properties of neurons.. but in practice of back-propagation learning, it is not needed. There are no "individual properties" of neurons, the weight values that result of your training cycles will differ every time. All initial weights can be set on a small random value, transfer threshold and learning rate are to be set per layer.
answered 2 days ago
Goodies
35416
We haven`t learned yet about learning patterns , ohh wait we did , supervised learning, this project is more of a GUI thing and so the teacher can see that we understand how a neural network should work, In a later project we will have to implement a network to solve a problem. And we will only be learning about feed forward, no back propagation.
– random_numbers
2 days ago
In that case I would keep it simple. User should specify the number of layers, the size of layers and a maximum random initial weight value for all weights. Use a single treshold function for all neurons.. There is one thing: you will need to set 3 learning rates in above case: when using hidden layers, user should be able to set different learning rates for each layer.
– Goodies
2 days ago
add a comment |
up vote
0
down vote
accepted
up vote
0
down vote
accepted
Looks nice ! You can have 3 hidden layers, but you'll see with experimenting, you will rarely need that many layers. What is your training pattern ?
Answer to your question depends on your training pattern and purpose of input neurons.. when e.g. some input neuron has a different type of value, you could use another threshold function or different settings for parameters in neurons connected to that input neuron.
But in general, it is better to feed neural network input into seperate perceptrons. So, the answer is: in theory, you could preset individual properties of neurons.. but in practice of back-propagation learning, it is not needed. There are no "individual properties" of neurons, the weight values that result of your training cycles will differ every time. All initial weights can be set on a small random value, transfer threshold and learning rate are to be set per layer.
answered 2 days ago
Goodies
35416
Looks nice ! You can have 3 hidden layers, but you'll see with experimenting, you will rarely need that many layers. What is your training pattern ?
Answer to your question depends on your training pattern and purpose of input neurons.. when e.g. some input neuron has a different type of value, you could use another threshold function or different settings for parameters in neurons connected to that input neuron.
But in general, it is better to feed neural network input into seperate perceptrons. So, the answer is: in theory, you could preset individual properties of neurons.. but in practice of back-propagation learning, it is not needed. There are no "individual properties" of neurons, the weight values that result of your training cycles will differ every time. All initial weights can be set on a small random value, transfer threshold and learning rate are to be set per layer.
answered 2 days ago
Goodies
35416
edited 2 days ago
answered 2 days ago
Goodies
35416
answered 2 days ago
Goodies
35416
answered 2 days ago
Goodies
35416
35416
We haven`t learned yet about learning patterns , ohh wait we did , supervised learning, this project is more of a GUI thing and so the teacher can see that we understand how a neural network should work, In a later project we will have to implement a network to solve a problem. And we will only be learning about feed forward, no back propagation.
– random_numbers
2 days ago
In that case I would keep it simple. User should specify the number of layers, the size of layers and a maximum random initial weight value for all weights. Use a single treshold function for all neurons.. There is one thing: you will need to set 3 learning rates in above case: when using hidden layers, user should be able to set different learning rates for each layer.
– Goodies
2 days ago
add a comment |
We haven`t learned yet about learning patterns , ohh wait we did , supervised learning, this project is more of a GUI thing and so the teacher can see that we understand how a neural network should work, In a later project we will have to implement a network to solve a problem. And we will only be learning about feed forward, no back propagation.
– random_numbers
2 days ago
In that case I would keep it simple. User should specify the number of layers, the size of layers and a maximum random initial weight value for all weights. Use a single treshold function for all neurons.. There is one thing: you will need to set 3 learning rates in above case: when using hidden layers, user should be able to set different learning rates for each layer.
– Goodies
2 days ago
We haven`t learned yet about learning patterns , ohh wait we did , supervised learning, this project is more of a GUI thing and so the teacher can see that we understand how a neural network should work, In a later project we will have to implement a network to solve a problem. And we will only be learning about feed forward, no back propagation.
– random_numbers
2 days ago
We haven`t learned yet about learning patterns , ohh wait we did , supervised learning, this project is more of a GUI thing and so the teacher can see that we understand how a neural network should work, In a later project we will have to implement a network to solve a problem. And we will only be learning about feed forward, no back propagation.
– random_numbers
2 days ago
In that case I would keep it simple. User should specify the number of layers, the size of layers and a maximum random initial weight value for all weights. Use a single treshold function for all neurons.. There is one thing: you will need to set 3 learning rates in above case: when using hidden layers, user should be able to set different learning rates for each layer.
– Goodies
2 days ago
In that case I would keep it simple. User should specify the number of layers, the size of layers and a maximum random initial weight value for all weights. Use a single treshold function for all neurons.. There is one thing: you will need to set 3 learning rates in above case: when using hidden layers, user should be able to set different learning rates for each layer.
– Goodies
2 days ago
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
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53238319%2fmultilayer-perceptron-questions%23new-answer', 'question_page');
);
Post as a guest
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
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
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
