All Questions

Filter by
Sorted by
Tagged with
1
vote
0answers
30 views

Is there any way to remove background of an image fully with the help of post-processor techniques(like edge detector) after deep learning based model

I'm using a deep learning model (deep lab v3+ with xception as the backbone) for image segmentation and removing the background. The subject of the image is a person. And my target is to extract the ...
0
votes
0answers
33 views

How is a time series with strong seasonality and trend stationary?

I was playing around with time series and stationarity and stumbled on something which I'm not getting completely. There are two popular ways of testing out stationarity - ADF and KPSS. And I was ...
1
vote
1answer
13 views

Do the examples of reinforcement learning such as the hide and seek learn to solve anything but the environment they start in?

As pictured here. https://www.youtube.com/watch?v=kopoLzvh5jY OpenAI implements a study for reinforcement learning with multiple learning agents which appear adversarial. "Millions of rounds&...
1
vote
0answers
11 views

Is there a list of neural style transfer architectures?

I'm trying to choose what neural style transfer architecture to use but I can't find a centralized list of all possible architectures I could choose from. Is there a place I could find this or could ...
1
vote
1answer
25 views

Elegant way to plot the L2 regularization path of logistic regression in python?

Trying to plot the L2 regularization path of logistic regression with the following code (an example of regularization path can be found in page 65 of the ML textbook Elements of Statistical Learning ...
0
votes
1answer
17 views

How to read data from BigQuery in pandas dataframe in PyCharm [closed]

I am implementing a new endpoint in a python-flask API, which should take the data from BigQuery and send it to the CloudSQL(mysql). For that purpose, I assume that first, a connection to BigQuery ...
0
votes
0answers
17 views

Latent Semantic Analysis on image features using k means

I have extracted Color Moments from a set of images and want to use Kmeans to perform dimensionality reduction and find the top k latent semantics. How can I use Kmeans for latent semantic analysis?
0
votes
0answers
21 views

Using Object Detection or Image Segmentation without labelled input data to build a dataset to then be manually labelled?

I'm looking to build an object detection model or image segmentation model, ideally the latter, which will identify and label objects from satellite imagery but I don't currently have any labelled ...
1
vote
1answer
38 views

Find feature categories associated with a specific target category

I have a Dataset with three columns. Products (up to 200). The quality checks that have not been conducted at the final quality check. (Up to 70 different Quality Control Measures) The result of the ...
0
votes
1answer
24 views

Compare model accuracy when training with imbalanced and balanced data

So I was recently doing a data science project which is a multi class classification. The project can be found https://www.kaggle.com/c/otto-group-product-classification-challenge. The dataset is an ...
0
votes
0answers
25 views

Is my choice of input space for a DQN problematic?

I am working on a reinforcement learning algorithm that attempts to solve a (discrete, finite) MDP with a non-Markovian reward function. It uses a DDQN with a large input space, which might be a bad ...
3
votes
0answers
36 views

Why margin loss is used in Capsule Network instead of Cross Entropy loss?

I'm reading the Capsule Network paper proposed by Hinton. I'm not sure why the margin loss is used instead of the cross entropy loss. Any intuitive explaination for this?
2
votes
1answer
11 views

cbind doesn't attribute the name of the column

I'm trying to create a new data frame that contains the row names and the first column of an existing data : i tried this ...
1
vote
0answers
25 views

XGBoost: How to obtain scale_pos_weight for multi classes?

I know there is a similar Qn at Unbalanced multiclass data with XGBoost. But I don't understand the reply provided by @Esmailian. What is the actual formula to obtain 1, 0.333 and 0.167? ...
1
vote
1answer
24 views

HuggingFace hate detection model

I am trying to train and evaluate a hate detection model using the HuggingFace Transformers library and this dataset. Model performance is secondary, just trying to get it going. I have preprocessed ...
3
votes
1answer
52 views

What are the most known ML-models that use complex numbers? (if there are any)

Basically just the header. The question is out of curiosity as I haven't seen one yet.
2
votes
1answer
43 views

Kernel trick derivation: why this simplification is incorrect?

I am trying to derive kernel trick from linear regression, and I have a mistake in the very end, which leads to an expression too simple. Basic linear regression For a basic linear regression (with no ...
1
vote
0answers
8 views

Building a simulator for continuous state, discrete action reinforcement learning

I am trying to build a simulator that optimizes the performance and temperature of a device. I want the device to perform well, but without making the device too hot. If the device becomes too hot, I ...
2
votes
1answer
29 views

Can I compare two models trained on different but similar datasets to help find differences between the two datasets?

I have a multivariate dataset the contains A and B. I want to see if there are differences between the A and B samples. I currently have two ideas on how to do this, but I am not sure if they are ...
0
votes
1answer
22 views

Query regarding the 'Data type' of features in Machine Learning

Should all the features in a dataset be converted to the same data type? For instance, if all the features have numerical values, some int & some float, should they all be converted to float? What ...
0
votes
0answers
14 views

Pytorch ANN not working with batch input. [ValueError: Expected input batch_size (1) to match target batch_size (64)]

I am encountering the following issue that my CBOW model that I have build using PyTorch is not returning individual values for batch input. It rather just returns a value for the first sample from ...
-1
votes
0answers
7 views

model stuck in first epoch

Every other model is running in seconds on M1 Macbook but this is model is taking infinite time to run the epochs.I am not able to identify the problem here.The same code is working fine in google ...
0
votes
0answers
25 views

ML techniques for subscription data

What are the ML methods one should use for subscription data comprising of visits, monthly active user, user interaction, product usage, location, source. predicting cost for our services.
-1
votes
0answers
18 views

What approach to solve problem of maximizing # of products sold with the constraint of maintaining an average profitability %?

I am working on a reinforcement learning model which recommends products to customers. The goal is to maximize the # of products sold, while maintaining an rolling average profitability of 2% for the ...
1
vote
0answers
44 views

Long term mathematical side effects of overfitting a model to reinforce a behavior

I have a neural network I designed, and previously I got this network working with some considerable simplification to its design which I was not fond of making. However I noted that during training ...
1
vote
0answers
31 views

How to handle unclassifiable data in the dataset

Premise: Classification problem Input is three text fields Output classes are A, B, A&B (Note: A and B are not always exclusive though usually are, hence the 'A&B' class) Sci-Kit Learn is the ...
0
votes
0answers
25 views

meaning of shapley values using SHAP

I have a binary classification - "BAD" and "GOOD" samples. The features are binary as well, either 0 or 1 (each sample is a boolean vector of size 264. I got about 3000 "BAD&...
1
vote
0answers
12 views

Finding clusters of 2D points when the metrics changes with spatial spread of points in each cluster (i.e., clustering output)

I am trying to calculate (a given number of) clusters of 2D points. However, I can't apply any conventional algorithm I'm aware of, such as k-means, as I need the clustering metrics to depend on the ...
1
vote
0answers
16 views

Practical Interpretation of PCAs for a supplier analysis

I am using PCA to validate and research a set of 13 suppliers of products against a set of about 50 variables and performance indicators against an ideal "wish"-Supplier, mostly based on G. ...
0
votes
0answers
7 views

Graph partitioning in ML with defining a cost function

I have an unweighted directed graph and I am searching in ML for an algorithm to divide this graph into subgraphs. I do my research and I found that most of the algorithms depend on the minimum cut. I ...
0
votes
0answers
9 views

Move data from BigQuery to CloudSql [closed]

How to create an endpoint in an API and move historic data from BigQuery to CloudSQL. The script should take start/end dates as parameters. Please help..
1
vote
0answers
21 views

Does time-series dependence penalize prediction with CNNs?

I'm trying to use CNNs on time series data (EEG), measured on different people. Each person has 10-20 recorded signals of different lengths and every subject has one global class assigned. Example: ...
1
vote
0answers
12 views

Is it possible to see the output for each layer in a mlp? using SKLearn

I have a simple NN which I have made with SKLearn. I have extracted: The weights sent to each node The bias assigned to each activation function But I can't see a way to get the output of the ...
0
votes
0answers
23 views

Import error _euclidean_distances from sklearn.metrics.pairwise [migrated]

I am working with Orange 3.30.1 trying to use the Python Script widget to add SMOTE to my data classification problem (the Orange team has refrained from implementing it, and suggest this way instead: ...
1
vote
1answer
19 views

Do I have to remove features with pairwise correlation even if I am doing a regularized logistic regression?

Normally we would remove features that have high pairwise correlation with another feature before performing regression. But is this step necessary if I am applying L2 regularized logistic regression (...
2
votes
1answer
59 views

Decision tree Why is Gini index only used for binary choices?

I would like to understand why "Gini index operates on the categorical target variables in terms of “success” or “failure” and performs only binary split" ? Why it would not be possible to ...
1
vote
1answer
35 views

Working with three types of data: numeric (integer, floats), images, and text for prediction

So I have three types of data (in title) and am wondering how I can combine the data. The target is numeric (price). My idea is to perform feature extraction on both the images and text, which would ...
0
votes
0answers
15 views

fast detection of mislabelled data samples

I have about 20% mislabelled samples within my dataset and I am looking for "fast" ways to detect them, one way that occurred to me: step 1: build a classifier (with k fold) on the dataset ...
1
vote
1answer
14 views

How does T5 model work on input and target data while transfer learning?

I am working on a project where I want the model to generate job description based on Role, Industry, Skills. I have trained my data and got the resultant output. I ...
1
vote
0answers
16 views

Comparing imputation strategies on a data set with no missing value

I am trying to evaluate a few data imputation methods and I am trying to see which one has a more accurate result. I have a dataset with no missing values(called X)....
0
votes
1answer
13 views

How to apply entropy discretization to a dataset

I have a simple dataset that I'd like to apply entropy discretization to. The program needs to discretize an attribute based on the following criteria When either the condition “a” or condition “b” is ...
-1
votes
0answers
13 views

Best way to train a model having train/test/val set [closed]

I have a dataset structured as well: X0: the first part of my time series where there are no anomaly values. I have x0_train which is the train set, x0_test which is the test set and x0_val which is ...
0
votes
0answers
12 views

Do Machine Learning algorithms uses all the provided dataset to perform a model? [closed]

I believe that machine learning don't use all the dataset in performing a model, more specifically, it should have a part of the data that is a garbage set where the model ignore it or it doesn't help ...
3
votes
0answers
21 views

Understanding an MLP coefficient array

I have implemented a super simple MLP using SKLearn. I have a 2 hidden layer model and 31 features on the input layer. So the lengths of the arays are 31, 20 and 10. ...
1
vote
0answers
12 views

Low-value coefficients in logistic regression

I prepared a logistic regression model. I then checked the coefficients/weights of the features, some of which were close to 0, which means these features do not contribute much to our predictive ...
0
votes
0answers
9 views

Compare multiple confusion matrix with unbalanced data?

I have a dataset with about 240k points, where the first 30k are "normal" (first class) and all the other 210k are considered anomalies (second class). I have applied on it four different ...
0
votes
0answers
6 views

Fusion (concatenation or elementwise) of coarse (deep) and high-res (shallow) features in ResNet, FPN and UNet

I understand this functionality, but I've neither the intuition nor reasons why this works. I'm looking at three cases of this fusion: ResNet, UNet and Feature Pyramid Net (FPN). In ResNet, in each ...
2
votes
0answers
24 views

Why there is a marked difference in metric scores using linear regression or MLP as readout for echo state network?

I am using a reservoir computing architecture comprising of an echo state network as per the paper Reservoir Computing Approaches for Representation and Classification of Multivariate Time Series ...
2
votes
0answers
24 views

Can I rescale TF matrix or TF-IDF matrix using StandardScaler prior to Logisitc Lasso regression?

I am trying to use Logistic Lasso to classify documents as 1 or 0. I've tried using both the TF matrix and TF-IDF matrix representations of the documents as my predictors. I've found that if I use the ...
2
votes
0answers
13 views

Adding data in PyTorch that will not be in features or labels

I have a neural network that I'm training on a set of 7 features, but would like to also add an extra data array that is not going to be a feature or a label. Specifically, I'm training a network to ...

15 30 50 per page