# All Questions

31,455 questions
Filter by
Sorted by
Tagged with
4 views

### each class distribution in a classification problem

Can we tell that the distribution of each class differs and the distribution of dataset is the combination of the classes distribution? What can we infer about the class distribution?
2 views

### KL divergence as loss for classification

I want to use KL-divergence as a loss function for classification problems. For example, consider the dog and cat image classification problem where I designed a CNN model with Softmax as output layer ...
6 views

### Pytorch different result when using torch.matmul and for-loop to pass input through linear layers

I have been at this for about two days now. I am working on a model that takes on an input x and passes it through several linear layers, and concatenates the ...
4 views

### How to revert np.log(data) and data.diff()?

I have used np.log(data) and then applied data.diff() to transform my data in timeseries model. I have the predictions. How do I ...
5 views

### Why does a linear regression in time series forecasting does not provide a line in predictions?

I'm reading the TensorFlow Time Series forecasting Tutorial 1 trying to perform my own time series prediction. However, specifically on single-shot models section for multiple time steps, the Linear ...
9 views

### Relationship of cost function to regularisation

lets say my cost function C(w)=DataLos(w)+1.Regt (w). Assume that the global minimum of C(w) when , 1 is 23. Now we change à to be equal to 10 and again minimize C(w). Does my optimal cost function ...
6 views

### BERT vs GPT architectural, conceptual and implemetational differences

In the BERT paper, I learnt that BERT is encoder-only model, that is it involves only transformer encoder blocks. In the GPT paper, I learnt that GPT is decoder-only model, that is it involves only ...
7 views

### error: (-215:Assertion failed)

I was testing OpenCV with their code provided within the documentation. Unfortunately, I'm facing an unexpected error. I think, it might be due to the newer version that I've. I've tried the fix of ...
7 views

### I am not sure whether I am being asked to calculate the variance or the irreducible error

The question: Suppose we randomly sample a training set D from some unknown distribution. For each training set D we sample, we train a regression model to predict $y$ from $x$. We repeat this 10 ...
6 views

### How to extract rules for decision tree from ID3 classification

I am working on a program to implement the ID3 algorithm. The program takes in user input for setting a threshold and creating a decision tree. ...
9 views

### Increase accuracy through "overfitting" multiple models?

I am currently trying to create a model to classify 5 specific classes from the coco dataset. I am using the object detection app from tensorflow. My question is: Will it be better if i: -Train one ...
8 views

### Siamese netwroks - how to choose loss function?

I have read several articles about siamese netwroks, and I understand that there are 3 different types of loss functions: ...
5 views

### Measuring the distance between data points based on mutual linkages

How to measure the distance between two data points (or: nodes?) based on their mutual share of linkages? I don't know the technical term for that, so here is a fictitious example from scientific ...
12 views

### What should I visualize for humor detection model to gain some useful insight?

I was going through bunch (1,2,3) of humor detection paper. But most papers don't include any visualizations, say some graph related to model being trained. I was thinking to train some language ...
7 views

### Expected input for time-series transformers

I am trying to create a model starting from the Attention is all you need paper. Specifically I want to setup the Encoder/Decoder architecture to predict time-series. I would like to implement it in ...
14 views

### K-Fold cross validating with random forest - how to correctly fit model to every fold?

So I have created K-Folds from my data using this code: ...
7 views

### Automatically finding business opportunities in text documents

I am new to machine learning and NLP. I am exploring the possibility of using one of these approaches to automatically examine a large collection of text documents and determine, first of all, if they ...
12 views

### How to preprocess heavy MRI images?

I have a large MRI dataset for an image segmentation task that cannot directly fit in memory in Colab, you can access the data with the link I put at the end. They are brain MRI images: 484 training ...
11 views

### Text Classification for columns with numbers, string and special characters

I have a dataframe with 3 columns and 1 label Here is an example of a row ...
25 views

### How to implement ID3

I'm trying to follow the suggested outline form implementing ID3 ...
11 views

### Correct Machine Learning approach for prediction using multiple timelines

I am wondering what would be the correct ML approach in order to predict the upcoming value of a time serie based on the previous behaviours of various time series for the same period. To explain ...
12 views

### "No gradients" error with a black box custom layer | TensorFlow

I'm trying to create a neural network where given the pure initial state of a quantum circuit (2D-vector), it spits out 2 numbers that would be essentially fed into a quantum computer to get results ...
10 views

### Why do I get this result with a chi square test?

I have a question about the chi square independence test, I'm working on dataset and I'm interested in by the link between the categorie of product and the gender, I plot my contingency table. ...
10 views

### Drop or impute the missing values?

I am working with a dataset having 45k rows and I was a bit confused on whether or not to drop the missing values OR impute the missing values. Column wise missing value distribution : As per this ...
13 views

### Constrained ANN

In my model, I use a twin network (Siamese) for which the training datasets are called positive class (u__{i,pos}) and negative class (u__{i,neg}). The anchor (u__{anchor}) is a fixed training ...
16 views

### Text clustering model on small dataset

Is there any way to run any clustering model on a small dataset with 290 text records (minimum character size is 100)?
15 views

### Creating numeric word representation of input sentences resulting in MemoryError

I am trying to use CountVectorizer to obtain word numerical word representation of data which is essentialy list of 160000 English sentences: ...
8 views

### Develop a Scorecard Model with Orange 3.30

I'm a super fan user of Orange 3.30, actually I've beeing develop some Collection Strategys and some othe of CLI in my actuall work, and everything has been OK with all the decisions that I've being ...
18 views

### How to learn common sense constants? Look in body for detail

If I wanted to learn constants for example week -> 7 days, chicken -> 2 legs, day -> 24, 1km -> 1000 meters hours, and so on, would it be possible to extract this information from a BERT ...
26 views

### Picking the right NLP model to tag words from a dataset

As the title suggests, I am posting here in the hope someone could direct me towards NLP models for tagging words. To be more concrete, here is what I wish to do. I would like to build a flashcard ...
16 views

### Difference between the architectures of semantic and instance segmentation

My question is about the difference between the architectures of semantic segmentation and instance segmentation models. So, as far as I understand, a semantic segmentation model is making pixel-wise ...
20 views

### Fake News Detection Classifier approach

I have the dataset related to any domain like sports, entertainment, politics, etc. I just want to know that the approach I am using for fake news detection is valid or not. As I do not want to use ...
17 views

### What is the name of the knowledge visualisation that shows independent paths which occasionally converge at certain points? (photo inside)

If I had Data that looked like this: ...
16 views

### Generate fake model predictions according to desired precision/recall values

Lets assume I generate a random set of target labels for a binary classification with N elements and a certain frequency of the positive class (1), e.g. 10%: ...
13 views

### Threshold moving for classification - how can i assess the cost?

I have a binary classifier. When i used my model to make predictions about 4k out of 10k were predicted to be "Rich". I am predicting affluence. Normally in classification the cut off to ...
20 views

### Should I remove rows without target value?

I am new to data science so any help is appreciated. Thanks in advance. I have a data set with a few explanatory variables and a target column that contains the label of each row. However, some labels ...
21 views

### Clustering with Highly separable features

I noticed that in my dataset a particular column is highly separable where it splits the data perfectly into 5 distinct classes (re-evaluated where class2 means better than class1). I would like to ...
7 views

### Errno 32 Broken pipe, Gensim Error, NMF

I am using Gensim 4.1.2 and trying to build a topic model using NMF. I am finding optimum number of topics using Coherence score. However when I am trying to get coherence values using get_coherence(),...
17 views

### Important features for detecting malware on the network

I am trying to build a model (Machine Learning) in order to detect malicious network traffic. At first, I am trying classify network traffic as malware or benign. After predicting the malware part, I ...
10 views

### Keyword Imputation Using Machine Learning and NLP

I am fairly new to machine learning and data imputation so forgive me if I am using wrong words or not feasible ideas. I have a table as follows, with text in the Headline column and a list of ...
12 views

### Convergence of Sarsa($\lambda$)

Is there any theorem on the convergence of the Sarsa($\lambda$) Algorithm? I am currently working through the theory of Reinforcement Learning with the lecture by David Silver and the book of Sutton &...
34 views

### Theoretical maximum depth of a decision tree

During my machine learning labwork, I was trying to fit a decision tree to the IRIS dataset (150 samples, 4 features). The maximum theoretical depth my tree can reach which is, for my understanding, ...
7 views

### Lower bound of confidence interval of a test data

I am interested in studying the effect of increasing data samples for a regression model on train error and test error. For this I have used confidence intervals for different values of a sample data. ...
22 views

### What ML model to train on when using an adaptive learning rate - the most recent or the one with the least validation loss?

I am currently implementing an adaptive learning rate for a neural network, meaning the learning rate gets reduced (e.g., halves) every time the validation error plateaus for 3 epochs (exemplary, ...
17 views

### Transfer Learning and Batch Normalization layers

I am trying to use ResNet152 ( pretrained on imagenet) to solve a certain classification task. According to Keras, one strategy for transfer learning is that we do not use the Resnet classifier and ...
15 views

### Is it possible to perform additional learning on a pre-trained model with YOLO based on Darknet

I would like to have a capability of my object detection model to improve over time as the available dataset grows over time, but avoid re-training a model from scratch every time I want to update the ...
17 views

### What to do when your training Dataset fields for a classification model are not constant or change?

I am trying to train an image classification model by first passing training images through Google vision API to extract image properties such as color and then creating a training data set with ...
26 views

### Points to remember when embarking on an organization-wide turn to AI solutions

In our organization, we are currently in the phase of building up team, skills to automate and implement AI based solutions. So, we are very early in this AI journey. Right now, we are also working on ...