Ask Your Question

WreckItTim's profile - activity

2019-03-09 22:31:38 -0500 received badge  Nice Question (source)
2019-03-07 14:46:14 -0500 received badge  Enthusiast
2019-03-06 11:23:39 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

Ya I ended up just making my own mlp from scratch haha, I need the control. It’s just excel dude

2019-03-05 13:32:05 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

sjhalayka I am really confused why you gave me your code. This is a problem dealing with OpenCV?

2019-03-05 12:28:20 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

Hey LBerger I rewrote the question to be more clear what the problem is.

2019-03-05 12:23:32 -0500 edited question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP using UPDATE_WEIGHTS to graph error - broken I ran into this problem while trying to make a learning curve of an

2019-03-05 12:22:26 -0500 edited question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP using UPDATE_WEIGHTS to graph error - broken I ran into this problem while trying to make a learning curve of an

2019-03-05 12:03:53 -0500 edited question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP using UPDATE_WEIGHTS to graph error - broke Doing some benchmarks and I want to make learning curves, showing er

2019-03-05 12:03:03 -0500 edited question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP using UPDATE_WEIGHTS to graph error - broke Doing some benchmarks and I want to make learning curves, showing er

2019-03-05 12:00:52 -0500 edited question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP using UPDATE_WEIGHTS to graph error vs number of training epochs Doing some benchmarks and I want to make learni

2019-03-05 12:00:31 -0500 edited question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP UPDATE_WEIGHTS wonky Doing some benchmarks and I want to make learning curves, showing error versus number of tr

2019-03-05 03:07:24 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

Yes it’s a regression problem. The training data is still the same for both network1 and network2. Shouldn’t the random

2019-03-05 02:52:30 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

Yes it’s a regression problem. berak contionous responses are fine, I think one of us confused? Could be me. The traini

2019-03-05 02:51:09 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

Yes it’s a regression problem. berak contionous responses are fine, I think one of us confused? Could be me. The traini

2019-03-05 02:39:28 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

Shuffling data differently shouldn’t have that big of an effect on how quickly the error converges?

2019-03-05 02:27:38 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

What would be the point of trying the XOR problem?

2019-03-05 02:25:53 -0500 commented question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

It’s the same results if I comment out the random seed lines.

2019-03-04 16:05:00 -0500 edited question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP UPDATE_WEIGHTS wonky Doing some benchmarks and I want to make learning curves, showing error versus number of tr

2019-03-04 15:45:53 -0500 asked a question ANN_MLP using UPDATE_WEIGHTS to graph error - broken

ANN_MLP UPDATE_WEIGHTS wonky Doing some benchmarks and I want to make learning curves, showing error versus number of tr

2019-03-01 12:33:18 -0500 commented question termination criteria broken if you want to specify number of epochs

Thanks, I posted the issue on GitHub!

2019-03-01 12:33:10 -0500 commented question termination criteria broken if you want to specify number of epochs

Thanks, I posted the issue of GitHub!

2019-02-28 19:30:57 -0500 asked a question termination criteria broken if you want to specify number of epochs

termination criteria broken if you want to specify number of epochs cv::Ptr<cv::ml::ann_mlp> network = cv::ml::ANN

2019-02-28 19:21:00 -0500 commented answer Max ANN_MLP size?

Ya thanks dude. I found the issue, the termination criteria is BROKEN on OpenCV, See this line: https://github.com/openc

2019-02-28 18:38:33 -0500 commented answer Max ANN_MLP size?

I am not having any issues with number of nodes/layers. I am just using two layers with 40 nodes each. The problem is wh

2019-02-28 17:50:26 -0500 commented answer Max ANN_MLP size?

Ya my job right now is to determine if this problem is solvable with an MLP, sorry I can't talk about it too much becaus

2019-02-28 16:59:25 -0500 marked best answer Max ANN_MLP size?

Hello dev team,

I had some general questions on max MLP parameters: Max number of layers? Max number of nodes per layer (and is this dependent on the number of layers used)? Max number of epochs you can set for training termination criteria?

I know these numbers are directly limited by the size of the variable type used, but curious in implementation what the actual limits are.

Thanks! -Tim

2019-02-28 16:59:25 -0500 received badge  Scholar (source)
2019-02-28 16:59:24 -0500 received badge  Supporter (source)
2019-02-28 16:57:18 -0500 commented answer Max ANN_MLP size?

Thanks for the links to source code and response! From the train method here: https://github.com/opencv/opencv/blob/978

2019-02-28 16:44:18 -0500 received badge  Student (source)
2019-02-28 16:20:24 -0500 edited question Max ANN_MLP size?

Max ANN_MLP size? Hello dev team, I had some general questions on max MLP parameters: Max number of layers? Max number

2019-02-28 16:19:07 -0500 asked a question Max ANN_MLP size?

Max ANN_MLP size? Hello dev team, I had some general questions on max MLP parameters: Max number of layers? Max number

2017-10-04 17:57:48 -0500 edited answer MLP Activation Function - train vs predict

Okay so tanh(x) = sigmoid function = (1+e^(-2x)) / (1-e^(-2x)) so the activation functions are the same. The sigmoid fun

2017-10-04 17:56:48 -0500 received badge  Editor (source)
2017-10-04 17:56:48 -0500 edited answer MLP Activation Function - train vs predict

Okay so tanh(x) = sigmoid function = (1+e^(-2x)) / (1-e^(-2x)) so the activation functions are the same. The sigmoid fun

2017-10-04 17:55:39 -0500 answered a question MLP Activation Function - train vs predict

Okay so tanh(x) = sigmoid function = (1+e^(-2x)) / (1-e^(-2x)) so the activation functions are the same. The sigmoid fun

2017-10-02 02:48:29 -0500 commented question MLP Activation Function - train vs predict

Ya you nailed it. Smart thinking diving into the source code. I posted an answer to this.

2017-10-02 02:01:49 -0500 commented question MLP Activation Function - train vs predict

In the docs, http://docs.opencv.org/2.4/modules/ml/doc/neural_networks.html The sigmoid function is described in the top

2017-09-30 20:08:24 -0500 asked a question MLP Activation Function - train vs predict

MLP Activation Function - train vs predict Hey, so my question was for the developers. In the docs, it says that train