All Questions
Tagged with neural-network classification
307 questions
0
votes
1
answer
338
views
Using sigmoid in binary DNN output layer instead of softmax?
For a binary DNN, the output is $y_0 + y_1 = 1$ since they are the probability distribution, hence the sum must equate to 1. However, I've been told that $y_1$ is sufficient to represent the output of ...
- 183
-1
votes
1
answer
45
views
Neural Network Classifier Different result
I am using neural network for a binary classification problem (yes or no). My training data set is not that big (39,000 records). After using SMOTE to balance the target, I have 50 input variables ...
3
votes
2
answers
410
views
How do I use keras NN to classify data after training?
I have defined, trained and saved my tensor keras NN. Now that that is complete how do I use it output classifications to non training data?
...
- 55
2
votes
2
answers
55
views
Algorithm for sequences classification
I want to ask wich algorithm can I use to do a sequences classification , knowing that I have two classes (positive /negative), but training is done using data from one class only (positive).
Thank ...
- 634
0
votes
1
answer
33
views
Same classification given for neural network regardless of the input
I am using the MNIST classification tutorials on the TensorFlow website to create my own classification program to predict a footballers value using the FIFA 19 dataset. However, when I run my program,...
- 1
3
votes
1
answer
2k
views
Cost sensitive classification with individual cost
I'm currently sitting on a problem, where i'm uncertain if there is not a much simpler solution.
I'm trying to train a DNN with a dataset for a classification task that should be cost sensitive. ...
- 41
3
votes
1
answer
84
views
Preprocess image data to classify objects based on shape
Currently I'm trying to build a neural network that is able to classify different types of bottles on an image solely based on the shape. The bottles have no label and at first I only used beer and ...
- 31
0
votes
1
answer
34
views
Neural Network Classification Probelm
How can 2-layer networks be used to classify more than two categories?
Can it be done just by adding more units/nodes into the existing layers?
- 85
1
vote
1
answer
972
views
Accuracy and Loss in MLP
I am trying to explore models for predicting whether a team will win or lose based on features about the team and their opponent. My training data is 15k samples with 760 numerical features. Each ...
- 51
3
votes
1
answer
920
views
Why do we Softmax at all?
Why take softmax at all at the final layer for multi-class classification problems? For example softmax of the vector [1, .5]
Is [.621, .379]
I mean if we just took the straight ratio, it'd give me
[...
- 199
2
votes
2
answers
1k
views
Why do people use CrossEntropyLoss and not just a softmax probability as the loss?
I don't understand why one would add additional complexity to log, probabilities for the loss function of a classification Neural Network. What benefit does that have, as opposed to just using the 0-1....
- 199
9
votes
2
answers
687
views
How to implement hierarchical labeling classification?
I am currently working on the task of eCommerce product name classification, so I have categories and subcategories in product data. I noticed that using subcategories as labels delivers worse results ...
- 171
2
votes
3
answers
245
views
which classification model allows user to choose importance of data inputs?
I am working on a match analytics project where I have to deal with the situation in which I am having some inputs like skills, experience, certifications etc. and my output is candidate selected Yes ...
2
votes
0
answers
2k
views
Why is recall so high?
I've built a binary classification model based on Keras and I am getting about 70% accuracy, and about 72% precision and 88% recall, making up to 79% F1-Score. I've tried different data models (...
- 1,067
66
votes
5
answers
206k
views
How to get accuracy, F1, precision and recall, for a keras model?
I want to compute the precision, recall and F1-score for my binary KerasClassifier model, but don't find any solution.
Here's my actual code:
...
- 1,067
4
votes
2
answers
7k
views
What could explain a much higher F1 score in comparision to accuracy score?
I am building a binary classifier, which classifies numerical data, using Keras.
I have 6992 datapoints in my dataset. Test set is 30% of the data. And validation set is 30% of the training set.
...
- 1,067
0
votes
1
answer
3k
views
Accuracy keep changing by changing randomState of classifier
I try to classify car sound samples. Using MLPClassifier from Scikit. I'm getting very different and confusing test results between 2 different test sets, and I am stuck:
Training is done with the ...
- 195
0
votes
3
answers
49
views
How to classify images Neural Network didn't trained to Understand
Let's say I trained a Convolution neural network to Identify Cats , Dogs and wolves . But suddenly I feed it pictures of rabbits and Lions. so how can I classify those as pictures as "Other"
I ...
- 103
3
votes
2
answers
2k
views
Using neural network for "features matching" binary classification
We have a dataset of numerical features from two images and we want to check if these images match or not using only these features.
Basically we have have these columns:
fA1, fA2, ..., fA14: 14 ...
6
votes
3
answers
1k
views
Is Overfitting always bad?
I have a data set of total 8000 sound samples. These are the results of my multi layer neural network, binary classifier:
...
- 195
4
votes
1
answer
2k
views
Connect a dense layer to a LSTM architecture
I am trying to implement an LSTM structure in plain numpy for didactic reason. I clearly understand how to input the data, but not how to output.
Suppose I give as inputs a tensor of dimension (n, b, ...
- 77
3
votes
2
answers
147
views
training neural network
I was given the task as follows,
Scrape articles appearing in Times of India since 2010 on HIV and AIDS. Classify them using training a neural network of your choice. Find patterns in those ...
- 131
3
votes
1
answer
64
views
Creating a neural network, composed of n times a different network. Is it possible?
I'm currently working on a project with a bunch of data of devices that can either belong to people, or not. The ultimate goal is to estimate a number of people detected.
Sadly, it is impossible to ...
- 163
5
votes
1
answer
198
views
Why doesn't neural networks use the concept of degree of freedom?
In most (if not all) NMIST neural network tutorials you will see that the last two layers reduce to a multi-layer perceptron (MLP) and the number of labels is 0-9 for a total of 10 labels. It is well ...
- 630
0
votes
2
answers
224
views
NN for fuzzy classification [closed]
What loss-function / optimizer to use for fuzzy classification problems?
E.g: Four categories hot, mild, cold, freezing.
Edit:
I use one-hot encoding and have ~ 60 datapoints.
- 3
1
vote
1
answer
924
views
Calibrate the predicted class probability to make it represent a true probability?
Let's say that we have a simple binary classification model (a neural network -- NN) for classifying input images as "dog" ($y=1$) or "not dog" ($y=0$). Let's assume that the NN has one "sigmoid ...
- 111
2
votes
0
answers
375
views
How to deal with unknown classes with a neural network classifier?
I have a small RNN with a softmax output, which succesfully classifies sequences within a known set of n classes. The model is only trained with known classes.
Now I have the problem that there might ...
- 53
3
votes
1
answer
3k
views
Should estimated probabilities from multi class classification sum to 1
I am using a neural network with sigmoid activation function $h(z) = 1 / {(1+e^{-z})} $ in order to classify image data into 6 categories. When running the trained neural network over new image data, ...
- 133
2
votes
0
answers
2k
views
Training multi-label classifier with unbalanced samples in Keras
I'm trying to train a keras model that takes in samples, let's say $x_i$ for sample $i$, and predicts multiple independent labels, $\hat{y}_{ij}$, such that $\hat{y}_{ij} = 1$ if the model predicts ...
- 121
1
vote
0
answers
49
views
Generating labeled dataset for training a neural network
I am currently working on a project in which i'm supposed to classify whether an image contains a translucent watermark or not. This is hard to do with standard object classification or template ...
- 11
2
votes
1
answer
938
views
Binary classification model with time series as variables
This is probably a simple question. Assume I'm interested in modelling a binary variable, with various covariates, including ones that are time series observations. In the usual modelling approach, ...
- 236
1
vote
1
answer
274
views
How does combining neurons create non-linear boundaries?
I have been working with NNs for a while, but haven't dug too deep into this unfortunately.
By looking at the three neurons below, in each of their boxes we can see that they are really just making ...
- 167
1
vote
1
answer
647
views
Multi-Class Neural Networks | different features
This may be a wrong question or something so feel free to correct me :).
I have been studying neural networks for weeks now. I came across the multi-class classification model that uses neural ...
- 257
1
vote
1
answer
408
views
How to use auxiliary target variables only present in train data
Imagining in my train data I have 3 target variables y1, y2 and y3, all binary.
My main goal though, is to predict the final variable Y = y1 * y2 * y3.
What should be the approach of a model when ...
- 73
1
vote
1
answer
60
views
how to split available data into training and testing (Information security)
I was advised to ask my question here.
Recently, I made a post about finding suitable dataset for SIEM (Security Information and Event Management) systems. The goal was to work on classification and ...
- 257
0
votes
2
answers
254
views
Best way to build a wave classification system
I want to make a classifier for waves such as following:
Above image is from: http://www.invisiblesbook.com/equal-temperament-tuning/
I believe, I will have to extract features from raw input using ...
- 1,578
2
votes
1
answer
41
views
Classifying objects based of a varying number of the same type of feature vector for each object
For a congressional session, I have created a doc2vec model of speeches made. Using the vectors from this model, I have a dataset of each congressperson, their political affiliation, and a list of the ...
- 145
7
votes
3
answers
11k
views
Neural network for Multiple integer output
I have a data set that contains 135 input features and 132 output values to be predicted. The input features are all numeric floating point values and each output value would be an integer between [0,...
- 73
5
votes
2
answers
119
views
What do neural networks learn first?
I'm running some experiments with NNs (actually I'm running an LSTM classifier), and I stumbled across a question I haven't found the answer so far.
What do NNs learn first? When we train a network ...
- 61
1
vote
0
answers
230
views
Cross entropy loss increase but precision get better
i am working on classification model.
my test result shows precision is getting better despite loss is increase.
is it just the nature of my data or is there some kind of theoretical explanation?
- 11
2
votes
1
answer
511
views
Neural network for variable length data classification
How can I create a network which can predict labels of variable lengths data:
Training data:
...
- 1,578
1
vote
0
answers
33
views
Are there cases where tree based algorithms can do better than neural networks? [duplicate]
I trained an image auto-encoder on a large dataset, and now have for every image, an n-dimensional feature vector. This vector is not spatially correlated to the image. I now used this embedding space ...
- 111
1
vote
0
answers
48
views
How can I make use of the labels subdivision in a Deep Learning Image classification? [duplicate]
I want to solve an image classification problem. I want to recognize cats and dogs. However my labels are more detailed than ...
- 63
5
votes
1
answer
70
views
What is the way to modify a neural network classifier to deal with sample points from outside of the label set?
I am solving an image classification problem. However some photos may not belong to any category, and I'd like not to give any fake information, rather to capture this situation. What are the ways to ...
- 63
1
vote
1
answer
2k
views
Prediction with unseen values in categorical variables
I have created an Artificial Neural Network with 4 features. I am at the point where I want to test the model with a live sample of a malicious file path/exe using:
...
- 224
1
vote
0
answers
48
views
Build algorithm for Price Prediction/Classification [closed]
lets say I have historical data for prices and some additional information like article, location and maybe text like "higher price in this area due to less competition". Important is, that prices are ...
- 19
9
votes
2
answers
237
views
Is there any consensus on choosing an appropriate ML approach?
I am studying data science at the moment and we are taught a dizzying variety of basic regression/classification techniques (linear, logistic, trees, splines, ANN, SVM, MARS, and so on....), along ...
- 155
3
votes
4
answers
374
views
k-means clustering or classification?
Why is choosing the k in the k-means clustering method based on a feature (take a dead or alive patients scenario as an example, k will be 2) considered clustering rather than classification?
- 31
1
vote
1
answer
34
views
Can I create pretrain model with tensorflow?
I takes a long time for train neural network model. It have to train every time when I run code. If I get high accuracy from training , Can I use same training model with another code without new ...
- 123
1
vote
1
answer
7k
views
Why is the softmax function often used as activation function of output layer in classification neural networks?
What special characteristics of the softmax function makes it a favourite choice as activation function in output layer of classification neural networks?
- 1,445