All Questions
Tagged with keras regression
84
questions
0
votes
0
answers
18
views
How to make my validation plots more stable and improve R2 metric?
I'm working on predicting 4 numeric values basing on signal spectrum (spectrum is represented as an array of 800 numeric values in scale 0 to 1). The input values are scaled by using StandardScaler. ...
- 1
1
vote
1
answer
33
views
Building a CNN (with Keras for pixelwise classification)
I have a set of 120x120 input images with 3 channels. I want to build a basic CNN to predict the value of each pixel. I have 2 doubts. One is regarding the last layer - should be a Dense layer, or a ...
0
votes
1
answer
352
views
Can I change the number of inputs to a keras model while preserving the trained existing weights
I have a simple Sequential keras model with 150 Inputs.
Some of these are simply OneHotEncoded values. Now I would like to add more options to the OneHotEncoder.
As an example: I previously had Blue, ...
- 3
1
vote
1
answer
375
views
Regression to fill NA values
As a part of an exercise, I have the following dataset. Note that I have no idea where the values come from (are they based on something real or are they random numbers? Don't know...)
...
- 111
1
vote
1
answer
898
views
How to compare $R^{2}$ of train and test data in a Deep Learning Neural Network Regression model?
I want to judge the goodness of my neural network regression model built using Keras Python Library. The problem is the following: from an input like (1000, 5000) so 1000 samples and each sample has ...
0
votes
1
answer
74
views
Energy Data Disaggregation with a regression model/LSTM
i am currently trying to develop a model, which takes a timeseries of mains energy data from a household as an input and should disaggregate this mains data in to specific device energy usage which is ...
- 1
0
votes
1
answer
387
views
How to fit a model on validation_data?
can you help me understand this better? I need to detect anomalies so I am trying to fit an lstm model using validation_data but the losses does not converge. Do they really need to converge? Does the ...
- 13
2
votes
1
answer
132
views
Loss function to prevent estimator bias
I have a regression problem I'm trying to build a model for: Predicting sales per person (>= 0) depending on some variables. I'm running different model types and gave deep neural networks a try. ...
- 31
1
vote
1
answer
281
views
How to compute threshold?
I would like to detect anomalies for univariate time series data. Most examples on internet show that, after you predict the model, you calculate a threshold for the training data and a MAE test loss ...
- 13
0
votes
0
answers
36
views
Different results in production vs evaluation - Keras
I have built a cryptocurrency regression model but it performs different in real-life then the evaluation over the same period.
I am using exchange binance. In production I call my custom the predict()...
- 1
5
votes
1
answer
5k
views
How to perform regression on image data using Tensorflow?
Overview
I understand the surface of the mathematics* of simple neural networks. I went through single-label image classification problems (ie using MNIST & fashion-MNIST datasets) using the ...
- 235
0
votes
0
answers
26
views
NN regression model predictions incomprehensible
I'm trying to build a deep learning regression model for price prediction of AirBnB listings.
As a baseline, I started with a simple 3-layer NN as follows:
...
1
vote
3
answers
2k
views
Predict next integer in sequence using ML.NET
Given a lengthy sequence of integers in the range of 0-1 I would like to be able to predict the next likely integer based on the previous sequence.
Example dataset: ...
- 13
0
votes
3
answers
12k
views
"ValueError: Data cardinality is ambiguous" in model ensemble with 2 different inputs
I am trying a simple model ensemble with 2 different input datasets and 1 output. I want to get predictions for one dataset and hope model will extract some useful features from the second one. I get ...
- 123
1
vote
0
answers
14
views
How to construct a graph using Neural Structured Learning framework?
My dataset (both features and label) consists of continuous variables. Dimension of features is (12,). The number of samples are of 7th order of magnitude (about 11 ...
- 111