ML model to transform words [closed] - neural-network

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I build model that on input have correct word. On output there is possible word written by human (it contain some errors). My training dataset looks that:
input - output
hello - helo
hello - heelo
hello - hellou
between - betwen
between - beetween
between - beetwen
between - bettwen
between - bitween
etc.
During preprocessing I add a measure of the distortion of a word. Then I hardcoding letters for numbers.
My current model's using CNN. The number of neurons of input is the same as the longest word in training dataset and the number of neurons of output is the same as the longest word in traning dataset.
This model doesn't work as I excepted. Word on the output is not look as I except.
eg.
input - output
house - gjrtdd
Question:
How can I build/improve model for this task? Is CNN a good idea? What other methods can I use for this task?

Related

Pressurized vessel in modelica [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 1 year ago.
Improve this question
I've been trying to create a pressurized vessel in openmodelica but i'm stuck.
The block i'm trying to build is a simple vessel for liquid pressurized by gas.
So two input ports (liquid input, gas input) and an output port for pressurized liquid outlet. The total volume of the vessel is constant. Looks simple but stuck with the duality gaz/liquid.
It's hard to provide any advice without your code. However, pressure vessels have been modelled in Modelica before and you could take inspiration from the following free libraries:
TRANSFORM: e.g. models in TRANSFORM.Fluid.Volumes
ThermoPower: e.g. ThermoPower.Water.Accumulator.mo
Buildings: e.g. model Buildings.Fluid.Storage.ExpansionVessel.mo

How do you do stratified sampling across different groups, when creating train and test sets, in pyspark? [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I am looking for a solution to split my data to Test and Train sets but I want to have all the levels of my categorical variable in both test and train.
My variable has 200 levels and the data is 18 million records. I tried sampleBy function with fractions (0.8) and could get the training set but had difficulties getting the test set since there is no index in Spark and even with creating a key, using left join or subtract is very slow to get the test set!
I want to do a groupBy based on my categorical variable and randomly sample each category and if there is only one observation for that category, put that in the train set.
Is there a default function or library to help with this operation?
A pretty hard problem.
I don't know of an in-built function which will help you get this. Using sampleBy and then so subtraction subtraction would work but as you said - would be pretty slow.
Alternatively, wonder if you can try this*:
Use window functions, add row num and remove everything with rownum=1 into a separate dataframe which you will add into your training in the end.
On the remaining data, using randomSplit (a dataframe function) to divide into training and test
Add the separated data from Step 1 to training.
This should work faster.
*(I haven't tried it before! Would be great if you can share what worked in the end!)

Difference between Array and Timeseries [closed]

Closed. This question needs details or clarity. It is not currently accepting answers.
Want to improve this question? Add details and clarify the problem by editing this post.
Closed 6 years ago.
Improve this question
I want to save result to to_file block in model matlab
just I want to know what is difference between array and timeseries in save format field.
Lets start from array - it's easiest thing. If you use To File or To Workspace block with array options it writes to file just column of values of your variable.
If you use Timeseries it writes values in timeseries format. This structure consist of several fields. Main of them are Time and Data. So you get not only values but times corresponded to this data! Furthermore it contain some additional information like interpolation method and other (see it in help).
When I have to use Array and when Timeseries?
It's clear that if time moments important to you you need to use Timeseries. For example if your simulation uses variable time step then data will not be uniformly distributed.So it's helpful to get times too.
Using an array is useful if times of data is not important. For example if I save from Enabled subsystem only 1 value of my variable.

NN stock prediction [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
I'm working on school project for NN(neural network) stock prediction I have my yahoo price market data and I normalised my data to number between -1 to 1 my inputs are date and close however I'm not sure what my output should be (I don't know enough knowledge about stock and market) I was thinking of having date and open as my inout and close as my output. I'm planning on using MLP for my project , but is there anything else I need to do after normalisation. I'm not expert on NN I'm taking this course to rise my total grade we were given only one week to finish this HW so I'm not sure if I'll be able to learn using new software
my inputs are date and open after normalisation what should be the next step
what neural network development tool do you recommend (for mac and PC)
can I use excel NeuroXL add on.. does it work on mac
Thank you

How to Test conditional independence between random variables using available samples? [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
How can I test for the independence between two random variable given another one(i.e. whether P(A|C)=P(A|C,B) or not?) using available samples. in other words, I just have 1000 samplesf for 3 random variables generated by bntoolbox on Matlab and now I wanna test for CI between arbitrary random variables.
I've read something about Fisher's method but honestly don't understand it.
Thanks is advance.