photo

Maria Duarte Rosa

MathWorks

Last seen: 2 years ago |  Active since 2017

Followers: 0   Following: 0

Statistics

  • Knowledgeable Level 3
  • First Review
  • Knowledgeable Level 2
  • First Answer
  • Revival Level 1

View badges

Feeds

View by

Answered
I want to implement Multilayer perceptron for software effort estimation. Which function should I use feedforwardnet, fitnet or something else.
For continuous outputs both fitnet and feedforwardnet are equivalent and the natural choice. Perhaps an easier way to get stra...

5 years ago | 1

| accepted

Answered
Custom Layer- Incorrent number of outputs
Hi Valentin, Thank you for your question. Multi-input/Multi-output custom layers are supported from R2019a. From your error me...

5 years ago | 0

| accepted

Answered
Mini batch size for SeriesNetwork
Hi Maxim, Thanks for providing more details. If your data is in a D x S matrix format (D being 2e6 and S being 15) MATLAB assu...

5 years ago | 3

| accepted

Answered
How can I use importKerasNetwork function to Import a pretrained VGGFace Keras network and weights?
Hi Ibrahim, you first need to install and run the python package as described in the GitHub page to obtain the model (including ...

5 years ago | 0

Answered
Correct weight Initialization in CNN
In R2019a, the following weight initializers are available (including a custom initializer via a function handle): 'glorot' (de...

5 years ago | 1

| accepted

Answered
How can I use importKerasNetwork function to Import a pretrained VGGFace Keras network and weights?
Hi Ibrahim, layers = importKerasLayers(modelfile) imports the architecture and weights of Keras models saved as .h5 files. Thes...

5 years ago | 0

| accepted

Answered
What is the order of the InputWeigths vector in a NARX net?
Hi Francisco, One suggestion is to use genFunction(net) to generate a MATLAB script from the trained network that contains all ...

5 years ago | 0

| accepted

Answered
How can we train images in matlab using Deep learning?
Please see here for different examples of how to use Deep Learning for Image Processing, including image super-resolution: http...

5 years ago | 0

Answered
weight balancing in pretraining networks.
Once can define a custom weighted classfication layer: https://www.mathworks.com/help/deeplearning/ug/create-custom-weighted-cr...

5 years ago | 0

Answered
How to customize Neural Networks' activation function
For Deep Learning networks one can create a custom activation layer using: https://www.mathworks.com/help/deeplearning/ug/defin...

5 years ago | 1

Answered
How to get deep learning layer output size?
Hi Itzik, Have you tried analyzeNetwork? https://www.mathworks.com/help/deeplearning/ref/analyzenetwork.html

5 years ago | 3

| accepted

Answered
deepdream error at cuda
Hi Michael, thanks for your question. deepDreamImage does not currently support DAG networks, such as GoogLeNet, and there is n...

5 years ago | 0

| accepted

Answered
what is the difference between LayerGraph and DAGNetwork in deep learning?
LayerGraphs and Layers contain the network architecture (for DAGs and Series networks, respectively). These objects are then pas...

5 years ago | 1

| accepted

Answered
How do I export a neural network from MATLAB?
The exportONNXNetwork function in Deep Learning Toolbox Converter for ONNX Model Format allows one to export a trained deep lea...

6 years ago | 2

Answered
Differences between "nntools" and "neural network fitting app"
'nntools' is an older GUI for neural networks comparing to 'nnstart' and the other GUIs featured in 'nnstart', such as the 'neur...

7 years ago | 0

Answered
LSTM Layer Architecture: LSTM units and sequence length
Hi Otto, The outputSize of a LSTM layer is not directly related to a time window that slides through the data. The entire seq...

7 years ago | 1

Answered
Neural Network: output representation (output layer)
Can you treat the problem as an object detection one? If so, then this example might help: <https://www.mathworks.com/help/vi...

7 years ago | 0

| accepted

Answered
Plot validation curve of Neural Network
Hi Jacky, When you work with imageDatastore you do not need to pass the files and labels separately into trainNetwork and als...

7 years ago | 0