# All Questions

26,320 questions
Filter by
Sorted by
Tagged with
23 views

### 2-label dataset for 3-label classifier?

I have a dataset containing headlines and sentiment related to those headlines. The headlines have been filtered out from another bigger dataset using the following criteria: keep the ones that have a ...
15 views

### Run python scripts on the cloud automatically [closed]

I need to run python scripts automatically on the cloud to stop depending on on-premise servers. This scripts would need to be run without any admin interference at least one time a day (they would ...
55 views

### Why don't we find the analytical function of the cost function?

Then we could derive it and find minimum(s). e.g. in small networks the cost function has not so many variables.
60 views

### Recommender Model for Human Action in Income Protection

Problem Domain I'm working on a project that involves building a model to provide recommendations on the next best step for Human supervisors to take on income protection claims. Income protection is ...
18 views

### Unsupervised Feature Scoring/Ranking [closed]

I have edited my post to: The context An E-Commerce website that want to recommend specific products based on the shoppers interest. The explanation I have a dataset with the following columns: ID: ...
31 views

### Does using your test set ultimately burn your data set in case of failure?

Given a data set I want to train a machine learning algorithm on. The data is split into training, validation, and test data. I now successfully trained my algorithm to work well with the training ...
20 views

Code: ...
30 views

### Why is IoU said to be non-differentiable?

I have been trying to find an answer online but I couldn't really find one. If anyone could help me I would appreciate it
24 views

### Binary cross entropy loss for one hot encoded 2 class problem

My aim is to predict whether a person is alive or dead. In the case there are two classes which can either be alive (1) or dead (0). The output could be only one class i.e 1 or 0 and not multi label ...
6 views

### Calculate values of a column of one based on data from another file [migrated]

I am newbie in python programming but I think it is the best language to program the solution to my problem. I need to multiply the values of a column of data based on the column name. The column data ...
32 views

### can an ordinary person act as a loss function? [closed]

the lost function tells the difference between a real image and a false one. Is there a job where multiple people act as a loss function? There is something like an interactive generative network, ...
30 views

### Is there any advantage of limiting the value of a feature in neural networks

In a machine learning algorithm, I have a feature that has a value in the range 0-20 it is very rarely value goes over 20 and if does I clamp it 20. Does it help the neural network model somehow using ...
22 views

### How are “data instances” sampled in Multiple Instance Learning?

My understanding of Multiple Instance Learning (MIL) for a weakly supervised problem, where we, instead of having a label for each data instance, we have a label for a "bag" of instances. ...
45 views

### How to build a model on a dataset having 40% missing values in most of the variables?

I have a huge dataset of 10 million observations but most of the variables are missing for 40% records. There are couple of variables available for the whole dataset such as sic code(Industry category)...
18 views

### Tree-based algorithms and ordinal features

For tree-based methods (e.g., DT, Random Forest, Gradient boosting, etc.), does the conversion interval of an ordinal feature to continuous matter matters? (I can see why it matters for linear model, ...
14 views

### How to implement large-scale Poisson Regression in Python

I am trying to implement a Poisson Regression in Python to predict rates. I am dealing with a ton of data (too much to store in a DataFrame), which means that using the standard statsmodels.api GLM ...
32 views

I just want to clear one doubt - we use gradient descent to optimize the weights and biases of the neural network, and we use backpropagation for the step that requires calculating partial derivatives ...
47 views

### Questions about a multivariate timeseries forecasting model - keras

I have trouble understanding the model I'm trying to create. I have few questions so I'll explain my model first and what I'm trying to do: I have created sequences of data (input and ouput of the ...
22 views

### Image Classification with CNN - class_mode='categorical' [closed]

I am trying to use a CNN to classify Images. Here is my code: ...
9 views

### Would descriptors of the last hidden layer of two different CNN be the same?

I am given a dataset of 2D medical images. I am asked to extract image descriptors from the hidden layer of the neural network pre-trained on the ImageNet dataset. I consider to use two networks: ...
10 views

### With one pretrained CNN model do I get only one vector of descriptors for an image?

I am given a dataset of 2D medical images. I am asked to extract image descriptors from the hidden layer of the neural network pre-trained on the ImageNet dataset. I consider to use two networks: ...
15 views

### Is it possible to guess a pretrained CNN accuracy beforehand?

I am given a dataset of 2D medical images. I am asked to extract image descriptors from the hidden layer of the neural network pre-trained on the ImageNet dataset. I consider to use two networks: ...
17 views

### In YOLO training, what if two objects' centers fall in the same grid?

As I know, YOLO predicts one classification result (as well as some bounding boxes) for each grid. But when training yolo, what if two or more objects' centers fall in the same grid? How to choose the ...
16 views

### How to choose variables to perform Exploratory Data Analysis

I have a dataset with about 110 variables. I have a target variable and I want to do an exploratory data analysis to find out what factors affect this target variable. In such scenarios when we have a ...
273 views

20 views

### Algorithm for Multivariable timeseries prediction (COVID forecast)

I am trying to forecast tomorrow's COVID-19 cases in my country. I tried a simple Linear Regression implementation based on the "new_positives" field but it does not work very well. I had ...
13 views

### I'm trying to fit a large dataset on Pipeline based model [closed]

The size of my dataset is 100,000 and it contains two columns (Input variable and Output Variable) My model code is: ...
27 views

### Using pretrained LSTM and Bert Models in CPU Only Environment - How to speed up Predictions?

I have trained two text classification models using GPU on Azure. The models are the following Bert (ktrain) Lstm Word2Vec (tensorflow) Exaples of the code can be found here: nlp I saved the models ...
43 views

### Rolling window features for multiclass classification [closed]

I'm doing a multiclass classification and data is considered as not being a time-series. Working on a feature engineering and trying to solve the problem with classic KNN, RF, boosting etc. I'm ...
21 views

### How does a neural tokenizer work? [closed]

I’ve been trying to build a NN tokenizer where the inputs would be chars and the outputs, tokens. But it is not clear to me how this kind of model should work in terms of the output format. If the ...
22 views

### Predicting which drug is most appropriate for which patient returns an accuracy of almost 0

I have a dataframe that looks like this: ...
8 views

### Autoencoder for Extremely Sparse Data

I am attempting to train an autoencoder on data that is extremely sparse. Each datapoint is only zeros and ones and contains ~3% 1s. Being that the data is mostly zero the autoencoder learns to ...
18 views

### finding the mean for each of the channels (RGB) across an array of images [closed]

How can I find the mean for each of the channels (RGB) across an array of images? For example train_dataset[0]['image'].shape is ...
34 views

### For a linear model without intercept, why does the redundent term in one-hot encoding function as intercept?

In this question Elias Strehle pointed out that if we keep all the levels during one hot encoding on a linear model without an intercept, the redundant feature will function as an intercept. Why is ...
8 views

### Why a GAN trained on same data and same parameters may produce different results?

I am trying to train a Generative Adversarial Network and ran the training a few times with same dataset and same parameters but it seems tp produce different results. Why this may happen?
15 views

### Basis Function Regression - Providing analytic expression - What to do with implicitly defined parameters?

within the probability distribution of p(y|x,w,c,d,a) c and d are implicitly defined within f(x). For a) I would have suggested: p(y | x,w,c,d,a) = N(y | f(x),a) My question: Is it okay to ignore c,d ...
25 views

### Classification of tabular data with a CNN [closed]

I am trying to build a CNN to classify tabular data. For that purpose i use a base image to convolve the feature vectors of my dataset to create a new image based dataset. (There is a paper about that ...
19 views

### Equation of a Multi-Layer Perceptron Network

I'm writing an article about business management of wine companies where I use a Multi-Layer Perceptron Network. My teacher then asked me to write an equation that lets me calculate the output of the ...
17 views

### Question about MLP and CNN

Can I use a MLP model architecture for taking a dataset with more than 10 features which are correlated to each labeled video frame along with a CNN that takes in solely the labeled video frame to ...
17 views

### What do the dimensions mean while using images in CNNs? [closed]

Please go through the code below. Image size is (32, 256 , 256 , 6). I don't think it is necessary to know what net is and what it does. My question is purely analytical. ...
12 views

### Variational Autoencoder with custom loss in Keras giving “nan” loss while training

I am trying to write a simple Variational Autoencoder for a numerical dataset as opposed to images such as MNIST etc. I am basically replicating the keras blog post on this subject (with obvious ...
21 views

### Confusion with the solution for this decision theory problem [closed]

$\textbf{I am given the following Decision Theory question:}$ Given a loss matrix with elements $L_{kj}$, the expected risk is minimized if, for each $x$, we choose the class that minimizes \$\sum_{k} ...
35 views

### Python sklearn model.predict() gives me different results depending on the amount of data [closed]

I train my XGBoostClassifier(). If my testing set has: 0: 100 1: 884 It attempts to predict 210 1's. Around 147 are wrong (False positives) and 63 1's correctly ...
18 views

### Does Keras allow using independant classifier

I have spam data set classified into 0:ham or 1:spam. I created the Embedding layer with Keras and then I used Conv1D following with other layers. My question is about adding a classifier like Random ...
6 views

### Right Package for Federated Learning

Could Someone list the pros and cons with respect to using federated learning with the following packages: TensorFlow federated PySyft Are there certain tasks which are specific to either or is one ...