All Questions
35,948
questions
0
votes
0
answers
16
views
how to define search space over hyperparameters automatically?
I'm trying to automate retrain steps of our ML models. My aim is hyper-parameter tuning with current data (newer performance window) using same algorithm and features on production environment. ...
- 1
1
vote
1
answer
29
views
I used SMOTE-ENN to balance my dataset and it improved the performance metrics, but how can I be sure it's not overfitting?
The models were evaluated using 10-fold cross validation.
foldCount = StratifiedKFold(10, shuffle=True, random_state=1)
The models in question are XGBoost.
...
- 15
0
votes
1
answer
22
views
How many parameters does the vanilla Transformer have?
The original Transformer paper (Vaswani et al; 2017 NeurIPS) describes the model architecture and the hyperparameters in quite some detail, but it misses to provide the exact (or even rough) model ...
- 163
0
votes
0
answers
5
views
Couldn't get the correct values after denormalizing LSTM Model
I couldn't get the correct value of the actual stock price after I denormalized the prediction value. The actual stock price should be around 150+-, however, after denormalizing it only shows around ...
0
votes
0
answers
5
views
Optuina pruning during CrossValidation, does it make sense?
I'm currently trying to build a model using CatBoost. For my parameter tuning, I'm using optuna and cross-validation and pruning the trial checking on the intermediate cross-validation scores. Here ...
1
vote
2
answers
43
views
How to boost the performance of a single decision tree by adding additional trees?
I have a binary classification task and the data has imbalance issue (99% is negative and 1% is positive). I am able to build a decision tree that is carefully tuned, weighted, and post-pruned. Take ...
- 11
0
votes
0
answers
17
views
how each tree in random forest structured/built?
I'm new to machine learning and I want to use random forest for the problem I have. What I have done so far is I did the 80/20 split of the original data set.
I need to understand what will happen ...
- 1
0
votes
0
answers
17
views
GitHub Archived Repositories
I'm trying to build a model that observes patterns of source control usage, from how many files are changed per commit, how many contributors there are, even semantic analysis on the commit messages.
...
- 101
0
votes
0
answers
12
views
How to fit datasets accounting for standard deviation in Python?
I have multiple datasets of measurements with standard deviation and I would like to fit all the data (with a non-linear regression model) accounting for SD or SEM (it is quite similar to let the ...
0
votes
0
answers
12
views
fine tuning open ai model with historical data
i'm trying to understand more about training models and unsure how to approach this problem.
I have a bunch of historical financial data that I would like open ai to use as additional context when ...
- 101
0
votes
1
answer
13
views
moments of weight vectors in Adam
When performing backpropagation with Adam algorithm, are the moment and the second moment of the weight vectors calculated also for the weights in hidden layers?
- 126
0
votes
0
answers
23
views
Where can I find gpt-35-turbo in the Microsoft Pricing calculator?
Where can I find gpt-35-turbo in the Microsoft Pricing calculator? I don't see gpt-35-turbo in the model list:
https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/ ...
- 5,488
0
votes
0
answers
7
views
Feature selection in high-dimensional datasets with sparse features
What are the most effective techniques for feature selection in high-dimensional datasets with sparse features in the field of natural language processing?
- 101
0
votes
0
answers
10
views
Word2Vec Data Leak
I want to train a machine learning model that can determine the sentiment of tweets about different stocks.
To do this I have a dataset, lets call it A. For dataset A about 30% of the data is labelled....
0
votes
1
answer
9
views
Unsupervised ranking of samples
Say I have a dataset of n samples. I want to maximize every feature’s value. I’m not sure if feature 1 is more important than feature 2, etc. Are there any methods of ranking my samples out there? If ...
- 1
0
votes
1
answer
19
views
How to cluster based on sensor data? - My first data science job
I'm on my first (real), data, programming job. As everyone can imagine, this can be quite hard and I learn a lot from it, given I am a data science student in university. However, I am completely ...
- 1
0
votes
0
answers
10
views
How to get same output with reference model
I have a tflite model which was working with a random script on swift and I decided to add some more classes on an object detection aim. Training with the new classes didn’t work. The first model was ...
- 1
0
votes
1
answer
12
views
Integrating time context in a machine learning model
Basically, what I'm curious about, are there any methods in machine learning to make the model take into account events that happen in real time that affect the data points during that time period. ...
1
vote
1
answer
12
views
Filling na values with condition from other column
I am working on famous titanic dataset and I want to replace na values in Age column but on such a condition that these people whose Pclass=3 receive 25, Pclass=2 29 and Pclass=1 38.
I was trying to ...
- 11
0
votes
0
answers
16
views
Why facenet works better than siamese network
I have been reading about face recognition literature. I stumbled upon siamese networks with contrastive loss and the facenet paper. Both approaches use metric learning. The difference is mainly in ...
0
votes
1
answer
325
views
ChatGPT: How to use long texts in prompt?
I like the website chatpdf.com a lot. You can upload a PDF file and then discuss the textual content of the file with the file "itself". It uses ChatGPT.
I would like to program something ...
- 23
0
votes
0
answers
21
views
General question on the test and train data
Currently I'm working on a Kaggle problem. I have to predict an outcome by the given information. There are few metafiles for training a model with lots of features (>30). However, in the test file ...
- 1
1
vote
1
answer
27
views
Making a netcdf data using xarray
I am very very new to the world of data science as I only started using it in my new job so I would really appreciate help from the community experts (maybe also in simple words :)).
I am trying to ...
- 113
1
vote
1
answer
26
views
Why the label is not explicitly involved in the loss function of skip-gram?
I am recently learning word embedding myself. When learning skip-gram from the paper https://arxiv.org/pdf/1310.4546.pdf[Distributed Representations of Words and Phrases and their Compositionality], I ...
- 11
0
votes
0
answers
16
views
How to get data directory in Microsoft Azure Machine Learning Studio
I am working on a CNN project, and I would like to read the data from an excel file. However, I am unable to find the proper path for it. I uploaded the data in the "Notebooks" file section. ...
- 3
0
votes
0
answers
12
views
What are the state-of-the-art knowledge distillation methods?
I need to implement some state-of-the-art knowledge distillation (KD) methods to distill dark knowledge of the teacher network to the student network with Pytorch.
I would really appreciated to any ...
- 1
0
votes
0
answers
17
views
Very different behaviors between PSI and KS tests for data drift
I want to set up a process for data drift and I am trying to see which metric to pick. Using KS test, it flags half of my features to be drifted although when I look at the distribution between the ...
- 61
0
votes
0
answers
9
views
Difference between Validation Error on Learning Curve and Validation Error Calculation in Machine Learning Model
I am encountering a problem where the validation error I see on the learning curve of my machine learning model is different from the validation error I calculate using the mean squared error function....
0
votes
0
answers
8
views
For Q&A NLP system, how to extract the most relevant embedding if it is a combination of top K embeddings?
From my understanding, a typical "AI" Q&A system has a (vector) database of embedded text (from a set of documents). And when a user asks a question, the user's question is embedded and ...
- 1
0
votes
1
answer
26
views
Maximizing minimum correlation
What meaning has the weighted sum of a group of variables so that each weight is assigned to maximize the minimum resulting correlation of all these variables to the sum obtained?
- 1
0
votes
0
answers
13
views
How to calculate threshold values for a simple binary classification model
Consider a binary classification problem with two features. Let's assume that the higher the value of each feature the more likely a datapoint is to be positively classified.
Additionally assume we ...
- 143
1
vote
1
answer
48
views
Convert cosine similarity to probability
In natural language processing, the cosine similarity is often used to compute the similarity between two words. It is bounded between [-1, 1]. Supposedly, 1 means complete similarity, -1 means ...
0
votes
0
answers
8
views
How to add query filter to the Nearest Neighbors algorithm?
I have Nearest Neighbors model, built with sklearn sklearn.neighbors.NearestNeighbors, which I use to make content based recommendations.
Sometimes I need to ...
- 101
1
vote
1
answer
12
views
What are the constants in this formula for polytrophic head?
Polytrophic head can be expressed as H = b1N^2 + b2NQ + b3Q^2 where b1, b2 and b3 are constants, N is the speed of the compressor (rmp), and Q is the volumetric flow rate of natural gas at the ...
- 175
0
votes
0
answers
6
views
Is there any way to aquire image and video URLs from a large amount of facebook ads for research?
I have aquired a lot of URLs to some political ads from the Meta ad library API. As far as i can tell, there is no way to automate the aquisation of the image and video URLs from these ads. Is this ...
1
vote
1
answer
20
views
Difficulty in Coding research papers
I've done a couple of beginner-level competitions on Kaggle, and I thought I should implement research papers in computer vision (YOLOv1) but I'm finding it difficult to code it. How should I proceed?
...
- 11
0
votes
1
answer
21
views
GPT-2 architecture question
I am currently working on a NLP model that compares two comments and determines which one would be more popular. I have already came up with an architecture - it will be based on GPT-2. But now I am ...
0
votes
1
answer
30
views
Understanding correlation - Machine Learning
I am experimenting a project on identifying cancer or not - Binary classification
The dataset has many columns. Here, I added correlation values between few input columns and the target column[cancer/...
- 21
0
votes
0
answers
6
views
ner transformers implementation in keras
I am following this keras link https://keras.io/examples/nlp/ner_transformers/
to train my own NER model. I am not clear why we have tags +=1 in the following ...
0
votes
0
answers
26
views
Multi-output Classification?
I have a dataset consisting of 1 X (Textual Data) and 5 different y (Topics of each text) and each y can take values from 0 to 5. I need to develop a deep learning model to take text and predict all y....
3
votes
2
answers
236
views
What techniques are used to analyze data drift?
I've created a model that has recently started suffering from drift.
I believe the drift is due to changes in the dataset but I don't know how to show that quantitatively.
What techniques are ...
- 523
0
votes
0
answers
21
views
How do I represent multiple seconds of video in tensors?
I want to use ResNet-18 for image features at the head of a VAE. If I have 10 seconds of video at 30 frames per second, and if ResNet-18 gives me the features of a single frame as a 512-dimensional ...
0
votes
1
answer
12
views
Do models of social systems suffer from prediction drift?
Background
I've created a binary classification model that predicts the probability of fraud for a given sample.
The choice of threshold allows me to set how many frauds are captured in the training ...
- 523
1
vote
2
answers
38
views
Neural network not learning at all
I am training a MLP on a tabular dataset, the pendigits dataset. Problem is that training loss and accuracy are more or less stable, while validation and test loss and accuracy are completely constant....
- 221
0
votes
1
answer
34
views
Why does Logistic Regression perform better than machine learning models in clinical prediction studies
I am developing binary classification models to predict a medical condition in my dataset. My results show that both Logistic Regression and Linear SVM consistently outperformed other ML algorithms (...
- 367
0
votes
0
answers
14
views
Subjectivity Classification with BERT and Word2Vec
I am new to NLP and working on a final-year project to classify if a sentence is written from objective or subjective point of view, using BERT with Word2Vec.
The datasets I found for this project are ...
0
votes
0
answers
30
views
How to combine two datasets to create training data
I am working on a problem where I have say dataset 1 (D1) and dataset 2 (D2), now D1 has three features F1, F2, F3, and D2 has four features F1, F2, F3, and F4. The number of samples in D1 is 7000 and ...
0
votes
0
answers
8
views
loss: NaN when training ucr timeseries set
I'm trying to change the input of this model,
https://keras.io/examples/timeseries/timeseries_classification_from_scratch/
the model architecture is as follow:
...
- 1
0
votes
0
answers
14
views
How can I use machine learning to identify groups in social deduction games?
I'm trying to write an algorithm to identify evil factions in the game Town of Salem. In Town of Salem, the mafia have to take over the town. The rest of the town (townies) must prevent this. To do ...
- 101
1
vote
1
answer
28
views
Why is my predictor value (continuous) perfectly correlated with my logit value (when testing logistic regression model assumptions)?
Question: Why is my predictor value (continuous) perfectly correlated with my logit value (when testing logistic regression model assumptions)?
Code:
...
- 11