All Questions
35,660
questions
0
votes
1
answer
5
views
How will a model handle real-life values in real-life applications without scaling?
I am learning ML and facing confusion about data scaling. For example, I have the following data:
Weight(KG)
Balance($)
75
3401542
99
4214514
Now, if I use StandardScaler, I may get something like ...
0
votes
0
answers
2
views
R Syntax for converting date to SAS date9 format but the date should be numeric and only format should change
Consider that I have a date i.e. 2017-10-23, and want the result to look 23OCT2017
...
- 101
0
votes
0
answers
2
views
Analysis to identify similar occupations by frequency of skills requested in job postings (in R)
I have access to a dataset of job postings, which for each posting has a unique posting ID, the job posting occupation, and a row for each skill requested in each job posting.
The dataset looks a bit ...
- 1
0
votes
0
answers
4
views
Vision Language Models Similar to DeepMind's Flamingo Available for Commercial Purposes?
Does anyone know of any Vision Language Models similar to DeepMind's Flamingo model that will take in a video clip a user provides the model along with a user-defined question in a prompt about what ...
- 111
0
votes
0
answers
6
views
Why are all PyTorch dataloader proccesses in S state (interruptible sleep) except one?
Short version: I'm using PyTorch dataloading library to load data in parallel for training a deep learning model. When I look at the CPU usage with htop, I see a ...
- 327
1
vote
0
answers
10
views
help interpreting training/validation curves for classification tree
I'm developing a binary classification tree and having some touble interpreting my training/validation curves. I used the CART algorithm with information gain as my splitting criterion. The training ...
- 111
0
votes
0
answers
3
views
Preserving the frontier while reducing dimensionality
I have this problem: reduce the dimensionality of the data such that points belonging to the frontier of the convex hull in high dimension stay relatively close the frontier in low dimensions. I do ...
0
votes
1
answer
8
views
Ways to share Pytorch model without revealing architecture?
We are trying to give a model to collaborators but would like to protect the IP. What are some ways to encrypt/hide/compile the definition when sharing a trained model?
- 1
0
votes
0
answers
5
views
Correcting 4-dimensional shape to 3-dimensional shape TCN
I am having issues correctly shaping the 3-dimensional layer in the model. Each time I run the code, I receive the error ...
- 1
0
votes
0
answers
9
views
Learning additional parameters that are not weights of a neural network
In addition to training the weights of a neural network, I also want to optimize other parameters (that are constant but satisfy some conditions over the entire data set). As an example, one can ...
- 101
0
votes
0
answers
9
views
Is Using Vertex AI To Check If Offers Will Be Approved Efficient And Cost Effective?
I am brand new here so please forgive any ignorance when asking this question. So recently my team started using Vertex AI for a few different tasks within our app. The latest thing we are looking at ...
0
votes
1
answer
13
views
Question about collapsing variable and oversampling minority classes
i have imbalanced data consisting of nine classes, and i am planning to collapse them into two classes. i performed stratified (proportionate) sampling between test, validation, and training sets ...
- 111
0
votes
0
answers
3
views
ExponentialSmoothing holtwinters with Keras Interace
Is it possible to wrap the statsmodels holtwinters with the Subclassing API in keras?
The reason i want to do it, is i have a WindowGeneratorthat creates me batches ...
0
votes
0
answers
6
views
Benchmark data set for Molecular genration
I'd like to test molecular generation using Pytorch geometric, I don't have any dataset to test it. PyG group is actully providing Graph AutoEncoder and Variational GAE, ARVGAE for such purpose. I can ...
0
votes
1
answer
12
views
Visualizing convolutional neural networks embedding
In this article, the author creates a graph (at the end of the post) from the embeddings of different words found by transformer model. I would like to do a similar thing for a convolutional neural ...
- 101
1
vote
1
answer
24
views
How to choose between different models with similar results? RF, GLM and XGBoost
I am a medical doctor trying to make prediction models based on a database of approximately 1500 patients with 60+ parameters each.
I am dealing with a classification problem (mortality at 1, 3, 6 and ...
- 11
0
votes
0
answers
10
views
Can I use macro recall to check if my RF model is overfitting?
I have a dataset with 837377 observations (51% to train, 25% to validation and 24% to test) and 19 features.
I calculated the recall score using average macro for train, validation and test and ...
0
votes
0
answers
9
views
Predicting a relative distribution between the available instances
I am working on a model that is supposed to predict how a given order volume distributes over the available articles in a retail scenario. For simplicity's sake, let's say I'm a retailer that buys ...
- 101
0
votes
0
answers
7
views
How to compare labels from clustering analysis and original ones?
I was asked to run a clustering analysis to assess the validity of labels for a manually labelled dataset.
I can simply save the actual labels (4 classes: 0, 1, 2, 3) and run clustering analysis (let'...
0
votes
1
answer
12
views
Is it necessary to have an additional "None" class for classification tasks for unknown inputs?
The idea is to have an additional class that would be "triggered" whenever there's an unknown/ambiguous input. Ideally, a ML model should do this by itself: it should for example return ...
1
vote
1
answer
34
views
Some answers given by ChatGPT are just beyond ridiculous, what could be the reasons?
Some answers given by ChatGPT are just beyond ridiculous, especially in Chinese (I am Chinese so I ask ChatGPT in both Chinese and English). Here is an example,
The last answer
...
- 111
0
votes
0
answers
14
views
The val_loss is nan, but loss is printing. Both train and validation losses are nan in model.evaluate(), and the acc improves during training
There is a 2-class classification problem, and my loss function is custom. The labels are categorical, and the final activation function is Softmax. During the training, the loss is printed, but the ...
0
votes
0
answers
3
views
What are the reasons that can lead to increase Micro F1-score but decrease the Macro F1-score
I have an imbalaced multi-label classification dataset
I tried these 2 models
First I used Bernoulli Naive Bayes algorithm that nativelly supports multi-label classification I got Micro F1-score of 45%...
- 517
0
votes
0
answers
2
views
Need an example to understand Entity and Relation Types in Knowledge Graphs
I tried to ask ChatGPT about this but still could not understand its answer and it seems to be a generic answer like it gives to most of my questions.
I could understand Entity Types, but could not ...
0
votes
0
answers
12
views
How does ChatGPT support languages except English?
How does OpenAI achieve multi-language support?
How did OpenAI do so many human-labeling works?
I guess OpenAI is using all the world users' feedback data.
- 631
0
votes
0
answers
6
views
Understanding Box plots
I am new to box plots and I am trying to understand it. Consider the following figures :
According to my understanding, outliers will exist after the max. line and before the min. line. So according ...
- 35
0
votes
0
answers
4
views
Designed Experiments: blocks, factors, treatments
I have recently began studying a course on Designed Experiments and am having some trouble understanding some of the terminology. I've looked at some other answers on the site and I think that I am ...
- 101
0
votes
0
answers
6
views
Is this GRU learning good?
Result seems to be a little out of "expected" values.
It's timeseries dataset.
- 101
1
vote
1
answer
14
views
probability distribution
Just wanted to know if the value we get by passing, say, random.normal(shape=(3,2)) in the Tensorflow, etc, are normally distributed or if they are randomly chosen ...
1
vote
2
answers
20
views
Dynamically remove data from training dataset
I was wondering today if it would be a good approach to remove data dynamically from the training dataset when learning a neural network. Assuming a classification task, the approach would be ...
- 524
1
vote
0
answers
11
views
How much data and computation power do I need to train a machine translation model using Transformer architecture?
I am working right now on creating a dataset to use in creating a machine translation model to translate between two dialects. I have two questions that I am trying to find an answer for:
How much ...
- 11
0
votes
2
answers
15
views
How to perform topic reduction?
I am using top2vec to perform topic modelling.
According to the paper, topic reduction can be performed on the topic vectors to hierarchically group similar topics and reduce the number of topics ...
0
votes
0
answers
30
views
Which Publicly Accessible Large Language Models are Very Similar to ChatGPT?
What other large language models exist or will soon exist that are VERY similar to OpenAI's ChatGPT in the sense of being fine-tuned or otherwise specifically created for conversational tasks ...
- 111
1
vote
2
answers
8
views
NN converges quickly but is it a problem when performance is good on test set?
I have an LSTM model I'm using for time series predictions. In training it converges already after 3 epochs. The model performs quite well on the test data, but should I still be concerned about the ...
- 11
0
votes
0
answers
5
views
Ground truth as a function of weights in Keras
I have a convolutional neural network that takes an image an outputs a value between -1 and 1. If the image is an array $I$, and the network transforms the array such that $\text{output} = f(I) \in [-...
- 71
0
votes
0
answers
20
views
How to handle multiple multivariate timeseries?
I am trying to develop a model using machine learning that reproduces a biological behavior. My goal is to do a regression of timeseries e.g from multiple input each time_step predict multiple output :...
- 29
0
votes
0
answers
7
views
Which F-metric to use in scientific paper?
Often, academic papers refer to F1-score, but don't explain which one they use (macro, micro, weighted). What is the common F-metric in academia?
- 101
0
votes
0
answers
9
views
Can not validate LSTM/GRU if return_sequences=True
As I understand the last LSTM before output layer should be set to
model.add(LSTM(lstmUnits, return_sequences=False))
but in such a case I can not validate while ...
- 101
0
votes
0
answers
4
views
Orange - Spectroscopy Widgets
There are many widget categories that I see in the manual but they are not available in the program. Do I need to load these categories? In particular, I am looking for the interpolate widget in the ...
0
votes
0
answers
9
views
Question about PCA cross validation & categorical data
I have been reading the book Hands of ML of Geron and a question arose for me the PCA you do after Normalization.
let's say u do a cross validation u do multiple PCA's, there could be a bug in some ...
- 1
0
votes
0
answers
16
views
Can neural network be able to convert analog timeseries to discrete timeseries
I have timeseries signal of sound echo back from instruments. They are firing kick, marker, wall, echo noise.
Since neural network can produce Seq2Seq prediction. I am using ResNet + 1DCNN to produce ...
- 111
0
votes
2
answers
17
views
how can I translate Whisper encodings to SBERT embeddings?
I'm using the Whisper model to recognize speech, and then matching the output text against a list of known questions by generating SBERT embeddings from the text and ranking the known questions by ...
- 101
0
votes
0
answers
10
views
How to build an image generation model for interior room design?
I want to build an image generator model for interior room design. This model should be able to generate interior image of living room/bedroom/hall/kitchen/bathroom. I have searched about it and found ...
- 11
0
votes
0
answers
7
views
LightningDataModule with Trainer in PytorchLightning automatically fits validation model?
I try to fight with overfitting, this is why I decided to look through documentation (https://pytorch-lightning.readthedocs.io/en/stable/common/evaluation_basic.html#train-with-the-validation-loop), ...
0
votes
0
answers
5
views
Orange 3 GUI Won't Start - Could not load the Qt platform plugin "xcb"
I'm using Pop!_OS 22.04 and have run the following commands to install Orange using pip. The install commands threw no obvious errors.
...
3
votes
0
answers
25
views
How Does the Reward Model in ChatGPT Calculate Losses?
Reading the InstructGPT paper(which seems to be what ChatGPT was built off of), I found this equation for the reward function.
However, I'm struggling to understand how this equation is used to ...
- 131
0
votes
0
answers
3
views
Multi Samples Belong to the same Person with one Label
i have acquired data from 8 person and this data is from the phone and saved in intervals (about 60 intervals per person), i want to use that Data for supervised learning to classify if a person is ...
0
votes
0
answers
3
views
How to give a column a special weight for any algorithm? (binary option)
I'm dealing with binary option, I'm making a classification model using xgboost, my idea is to predict the posterior candle color by using some data of the 20 previous candles so I made a dataset on ...
1
vote
0
answers
13
views
ValueError: Found input variables with inconsistent numbers of samples: [120, 30]
I practice XGBClassifier() to predict the target in iris dataset.
here is the code:
...
1
vote
0
answers
14
views
Memory usage of a DNN model during inferencing
I am running a DNN model (YOLOv7) on a GPU (GeForce 3080 TI) to detect objects in a video stream. The memory usage on my task manager shows that I am using up to 2GB of my RAM! The GPU Ram usage is ...
- 11