For questions about machine learning modelling, architectures and design choices, as well as traditional models (AlexNet, VGGNet, Inception, ResNet, etc).
Questions tagged [machine-learning-model]
131 questions
0
votes
1 answer
What do you do when you have an ML model that works, but does not have good results?
Sorry if this has been asked before, I have tried looking online but maybe I don't know the proper terminology because I mostly find results that try to address overfitting by splitting the data set.
So when my my models gets stuck at like 30%…
Xun
- 43
- 1
- 5
0
votes
1 answer
SVM Kernel's O(n) time
I can't understand how computing kernel, K(x,z) takes only linear time despite working in O(n^d) dimensional space.
Please explain me. I'm a newbie in ML.
Ashutosh Agrahari
- 71
- 7
0
votes
1 answer
Azure ML Prediction Is Constant
I am using the Azure ML model available at https://gallery.azure.ai/Experiment/Weather-prediction-model-1 to design a prediction mechanism based on temperature and humidity. I haven't done any changes to the existing model and feeding in data from a…
Sudeep Hazra
- 118
- 15
0
votes
2 answers
How to test a machine learning model?
I want to develop a framework(for QA testing purpose) that validates a machine learning model. I had a lot of discussions with my peers and read articles from the google.
Most of the discussions or articles are telling machine learning model will…
Siva
- 1,078
- 4
- 18
- 36
0
votes
1 answer
Using a saved model to test data through Java code (Weka)
I'm completely new to Machine Learning, so my understanding might be wrong in some cases. I'm trying to test data via loading a saved model through Java Code using weka.
Instances testingData = readArffFile(testFile);
try
…
user1340852
- 825
- 3
- 9
- 27
0
votes
2 answers
Is there a way to update a trained machine learning model in Weka while making predictions for new data (Java)?
I have implemented classification algorithms using machine learning using Weka Java. I would like to deploy the trained model on RasberryPi to test.. I want then the trained model get updated every time when it receive the new data and make…
Srivardhan Cholkar
- 130
- 1
- 9
0
votes
1 answer
XML to Azure ML Studio
i try to test ML Studio with some data stored in XML. However i tried a lot of things i.e. convert xml to csv, to JSON but didn't find a good way to use ML studio with this data.
The problem is not the conversion itself, It's just a problem of the…
Norbert Smith
- 19
- 4
0
votes
0 answers
iOS: No result from CoreML prediction, using model converted from Keras
The problem I'm facing is in Xcode 9 (Beta 5) my model's prediction call doesn't give any result, just hangs there, without error.
The requirement is to recognize one specific movement of user's phone, and exclude other similar movements. So my…
Dustin Jia
- 67
- 7
-1
votes
1 answer
Beginner started learning python and django. I want my dropdown to get data from my dataset
I'm trying to build a machine learning algorithm and then deploy it to my website using django.So here comes the problem I want drop downs on my forms and. Im using the select tag on html while creating my dropdown but it is very hectic to give each…
-1
votes
1 answer
Should we always first perform feature normalization and then the feature reduction?
Sometimes performing feature reduction reduces number of features with methods like PCA and then we could scale only the relevant variables. Is there a rule that we need to do normalization/scaling first and then the feature reduction?
Sharat Ainapur
- 19
- 8
-1
votes
1 answer
How many model parameters do we need to optimize for the following CNN model?
We use the following convolutional neural network to classify a set of 32×32 greyscale images (so the input size will be 32$\times$32$\times$1):
Layer 1: convolutional layer with the ReLU nonlinear activation function, 100 5×5 filters with stride…
Seyed
- 3
- 2
-1
votes
1 answer
Applications Using Machine Learning Without Cloud
I have seen various methods of deploying machine learning models on the cloud, but I just wanted to know if we can create a program that uses machine learning not from the cloud but instead uses the model trained on the same computer. What I mean is…
Anonymous
- 117
- 7
-1
votes
2 answers
How do you choose a neural network model for a particular purpose?
I am a beginner with very less knowledge about CNN & RNN.
For Eg: RNN works better for time series and CNN for spacial features, knowing this it might make easy for me to select between RNN and CNN.
Though, if I am made to make a choice between…
Vinit D
- 41
- 2
-1
votes
1 answer
How to balance your data-set when in the real world there isn't a constant balance
I can't decide how to balance my dataset on "distress situations" since it isn't something that can be measured as "the percentage of rotten apples in a factory".
For now, I've chosen to just use "50%-50%" of distress voice snippets and random…
21kc
- 23
- 5
-1
votes
2 answers
Unable to install tfcoreml (specifically coremltools)
I've tried a virtualenv, changing my python type to 2.7x, and installing it manually.
However, I keep getting the error of
Could not find a version that satisfies the requirement coremltools>=0.8 (from tfcoreml) (from versions: )
No matching…
