All Questions
35,948
questions
0
votes
0
answers
2
views
YoloV5 results rendered lead to different picture
I basically trained a custom model to detect peg-solitaire games.
In my example I use the results of the detection to render a board with matplotlib
...
- 157
-1
votes
0
answers
7
views
0
votes
1
answer
24
views
Why use tanh (or any other activation function)?
"In machine learning, it is common to use activation functions like tanh, sigmoid, or ReLU to introduce non-linearity into a neural network. These non-linearities help the network learn complex ...
- 103
0
votes
0
answers
8
views
Do exist Multi-output Deep Reinforcement Learning?
I need a deep reinforcement learning algorithm where the action is an array of N integer values. The idea is that given a state, the action that the agent will decide should be an array of N numbers, ...
- 1
0
votes
2
answers
20
views
Regression model doesn't handle negative values
I'm trying to create a model that, given a feature $x_i$, predicts $y_i$ such that $y_i=ax^2_i+bx_i+c$ by using backpropagation.
To do this, I'm using the ReLU activation function for each layer.
The ...
- 126
0
votes
0
answers
6
views
RNN using multiple time series for forecasting
I am trying to create a Rnn model to suppose, forecast weather. I have the weather data for a year recorded at multiple places and the dataset also contains other factors such as humidity, daylight ...
0
votes
0
answers
6
views
Techniques for choosing datasets from pool of datasets to create priors(time-series data, DTW? spike and slab?)
Let us consider a scenario where we have a pool of 100 datasets from various customers, with varying sizes containing sales and budgeting(mutiple channels) data per date. The datasets can range from ...
0
votes
1
answer
10
views
What is the relationship between robustness to Adversarial Attacks and Out-Of-Distribution OOD generalization?
You hear the word Robustness (defined as a model's robustness to spurious correlations ) a lot associated with Adversarial-Attacks and OOD Generalization and wonder how are these concepts interrelated?...
0
votes
0
answers
5
views
How can I separate and follow the plants that are very similar to each other with the YOLOv5 algorithm?
I want to differentiate between fern and mint using the YOLOv5 algorithm. Now I can take pictures of fern and mint, mark them on LabelImg, and train them in collaboration with Google. However, since ...
0
votes
0
answers
3
views
Is there a rule of thumb for the initial value of loss function in algorithm like word2vec?
There is a rule of thmub for initial value of of loss function in multi-class classification task:
$$loss=-ln(1/number\_of\_unique\_class)$$
By comparing inital loss with the loss aftered trainning, ...
0
votes
1
answer
25
views
Is my model overfitted?
I am using a naive bayes classifier to classify 20 newsgroup dataset. My accuracy on the training set is 97 and on the testing set is 89. Is my model overfitted?
If it is what steps can I take to ...
0
votes
1
answer
4
views
Training a Neural Network on standard deviation
Right now I have a training dataset that kinda looks like this (Image, Float) array, where the Image is independent variable and the float is the dependent variable:
...
0
votes
1
answer
14
views
Can I use LLM to explain codebase?
I am a Data Engineer, and I am currently assigned a task to refactor an outdated code and rectify any bugs present. However, I am unable to comprehend the code written in the existing codebase. ...
- 3
0
votes
0
answers
5
views
Is it possible to encourage a constitutional network to reduce the range of activations
I am trying to implement a statically-quantized convolutional network. A problem I am having is that the convolutional layers all tend to produce an activation tensor with a large range (roughly -10.0 ...
0
votes
0
answers
10
views
Reinforcement learning with Q-learning doesn't seem to be learning
I'm learning reinforcement learning with Q-learning and I made a training script for Flappy Bird. The problem is that it doesn't seem to be learning and I'm not sure why.
My guess is that there's ...
- 1
0
votes
1
answer
11
views
Best practice for variables that only have answer if yes in previous column
I currently have a dataset that consists of survey data that has several columns that have answers dependent on the previous question. For example, I may have a question that says "Did you take ...
- 23
0
votes
0
answers
11
views
How to label a transactions dataset made from scratch?
I have a question regarding creating a transactions dataset from scratch.
I've created customer profiles and am generating transactions based on these profiles. The way I do this is based on the ...
- 1
0
votes
0
answers
12
views
Role of $f$ Target Network in DDPG
I am trying to create a variant of DDPG in MATLAB that has no action-value $\langle Q \rangle$ net, but that instead works with networks $\langle V \rangle, \langle f \rangle, \langle r \rangle$, and ...
0
votes
1
answer
15
views
What is the best way to store large data when training a model?
This is rather a technical question, when training the model I import data locally to Google Colab runtime which does not seem to be efficient, when the runtime ...
- 101
0
votes
1
answer
18
views
Matching items in a recommender system
I would like to ask for a proposal for a machine learning model that would be suitable for the following problem:
I have a training set where each element of type A corresponds to a certain number of ...
- 41
0
votes
0
answers
15
views
ValueError: Found input variables with inconsistent numbers of samples: [283, 943]
I am trying yo split the data using train_test_split(), but I got this error:
...
- 1
1
vote
0
answers
9
views
How to interpret a Bayesian neural network prediction for binary classification in comparison to deterministic neural network?
Allow me to clarify my current understanding:
Interpreting a binary classification prediction made by a deterministic neural network
On one hand, point estimates fall on a sigmoid curve (between 0-1, ...
- 489
0
votes
0
answers
4
views
Cannot scale after Encoding
After splitting my training and test sets, I successfully encoded my categorical data but whenever I try to Normalize or Standardize the data, it goes back to saying "ValueError: could not ...
0
votes
0
answers
10
views
research papers on mean average precision
I've been coding YOLOv1 from scratch, are there any good papers which explain and/or give code (or pseudocode) for mean average precision? I searched but couldn't find good ones
- 11
0
votes
0
answers
5
views
Doubt with Forecast values with orange
I would be very grateful if anyone can help me with the following situation.
I have a table that receives seven data records with values from 1 to 43 at random, for example:
With SQL I can determine ...
- 1
0
votes
1
answer
32
views
Where do Kaggle Masters Work?
If you become a Kaggle Grand Master, it should increase your job prospects, but does it guarantee a job at a FANG company for instance is a question of interest.
0
votes
1
answer
25
views
Python Tensorflow - Predict human vs horses images always same value
I'm trying to follow a tutorial about Tensorflow in Python and computer vision.
In this exercise I'm using a pre-trained model (InceptionV3) and some image augmentation about a datasets of humans vs ...
0
votes
0
answers
8
views
Modeling time series with events data for ML
We have a business that provides analytics for institutional traders.
The data we provide is in the form of events (various market dynamics have changed, etc), temporal zones that describe specific ...
- 101
0
votes
0
answers
15
views
Determining clusters of time series
I have been given time series of N stock prices and time series of K sectoral indices. (Sectoral index is index made from all stocks belonging to that sector.) I have not been given names of any of ...
- 99
0
votes
0
answers
16
views
State-of-the-art LSTM solutions to known datasets
I've seen that many ML datasets have competitions (like imageNet).
I've been looking for some kind of competition or state-of-the-art LSTM solutions for The Airline Passengers dataset but all I can ...
- 101
0
votes
0
answers
8
views
zero shot model to improve accuracy
I have thousands of comments and I used Hugging Face's bart-large-mnli (https://huggingface.co/facebook/bart-large-mnli) to classify the comments into several topics that I entered in to the codes (i....
- 1
0
votes
0
answers
20
views
What is the steps to generate data from a plot and use them to have a predication using python?
I have a plot that represent a BH curve for magnatic material. The material have a behavior for each H value for two different temperature 25 C and 100 C. Figure 1. I need to extract the data for each ...
- 1
0
votes
0
answers
23
views
Regression with time series data
I want to predict temperature when time (datetime type, hourly data for five months) and humidity is given. Before starting in python, I created a regression model in excel. But instead of predicting ...
- 1
0
votes
0
answers
21
views
Common cross-validation code: why does it work?
The following Python code is common practice when creating a folds column for multi-label stratified k-fold cross-validation:
...
- 101
0
votes
1
answer
25
views
Deep Learning book - PCA - showing the covariance of z is diagonal
In the Deep Learning book at Page 146, the authors are showing that the covariance of the representation $z = W^T x$ is diagonal (Eq. 5.92 through Eq. 5.95).
The terms are conveniently arranged:
$$
...
- 5
0
votes
1
answer
12
views
0
votes
0
answers
17
views
Binary transformer classification model predicts everything as same value
I'm training a binary classifier using a transformer on structured numerical data (so the order of the columns in my spreadsheet matters). I have adapted the keras text classification model for IMDb ...
- 1
0
votes
0
answers
9
views
Facing Problems in Dilation and Erosion of Segmented Images of Knee X-Rays
I am working on a project to grade the severity of Knee Osteoarthritis using X-Ray Images. Before feeding the images into the machine learning model and enhancing the features of Knee osteoarthritis i....
0
votes
0
answers
6
views
Sampling strategies in multi-target classification
I am dealing with multi-target binary classifications (I have two targets). I need to use a sampling strategy. I have tried imblearn.pipeline but I'm getting the same error as this time when I'm ...
- 101
0
votes
0
answers
11
views
GridSearchCV using best paramters
i have got a question, i want to use GridSearch on a MLP and my question is after finding out best parameters do i have to train my model with the data again with the best parameters ?
0
votes
0
answers
6
views
How can I use an ontologyies schema to classify triples?
I have extracted some triples (Subject, Predicate, Object) from text using an information extractor.
How do I automatically establish where these triples fit into my pre-existing ontology? How can I ...
- 13
0
votes
0
answers
5
views
Fit multiple models e.g classifiers -> stacking -> calibration without data-leak or getting too many datasets
I have some data X on which I want to do the following:
Train two models; SVM and Logistic Regression
Use a stacking classifier based on the models from (1)
...
- 440
0
votes
1
answer
17
views
Quadratic regression with TensorFlow is not working
I want to make a TensorFlow model that, given features $x$ and labels $y$ such that $y_i = ax_i^2+bx_i+c$, predicts reasonably well the equation.
...
- 126
0
votes
0
answers
14
views
An algorithm to detect when the sound is not normal?
I was wondering the following problem: Suppose I have a machine and I would like to record its sound and detect automatically when the machine is going to break. What kind of algorithms are used to ...
- 1
0
votes
0
answers
13
views
How to split a LGBM.DataSet into trainning/validating/testing sets?
It looks like that LightGBM.train() can accept two arguments i.e. train_set and valid_sets, then it can do validating operations ...
- 101
0
votes
0
answers
30
views
How can I improve the inefficiency so the function actually completes?
How can I improve the efficiency of the following line:
X_df=pd.concat([X_df,pd.concat([pd.concat([dyn_df,stat],axis=1),demo],axis=1)],axis=0)
Which can be found ...
- 101
0
votes
1
answer
14
views
I have a question about Transformer's Q, K, V
I think the cosine similarity of negative values has its own meaning.
If you softmax the cosine similarity of Q and K, wouldn't it prevent Transformer from using information with the opposite meaning?
0
votes
0
answers
8
views
Using ML to suggest steps to solve network issues
Network support teams have runbooks that list steps the engineers need to take to troubleshoot a specific network problem or failure. Since troubleshooting each failure will have a series of steps ...
0
votes
0
answers
9
views
Feature engineering from HTML & CSS attributes
I have a bunch of HTML files, and inside each there's a particular occurrence of a "substring" which I need to find out. The substring can occur in any tag, and can also have multiple ...
- 101
0
votes
0
answers
18
views
which one is the best solutions a new activation function or customize own layer
when a new activation function is more suitable than the customize own layer? what is different of these? when we use from a new layer or new activation function.
we need model a fitness function, but ...
- 1