Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.

Sign up to join this community
Anybody can ask a question
Anybody can answer
The best answers are voted up and rise to the top

Top Questions

2 votes
2 answers
221 views

is there a deep learning model that handle 47800+ classes for classification?

0 votes
2 answers
95 views

ChatGPT's Architecture - Decoder Only? Or Encoder-Decoder?

1 vote
1 answer
55 views

Specifics about ChatGPT's Architecture

0 votes
1 answer
37 views

high degree polynomial model with sklearn does not fit

0 votes
1 answer
53 views

Read big JSON file as a Dataframe using polars

1 vote
1 answer
28 views

S-Shaped Learning Curve

0 votes
1 answer
27 views

How to calculate accuracy of a logistic regression?

1 vote
2 answers
26 views

Validation accuracy almost zero while training accuracy much higher

0 votes
1 answer
19 views

Does a neural network need to be retrained on both old and new data?

1 vote
1 answer
24 views

Timeseries (InfluxDB): How to deal with missing data?

0 votes
0 answers
24 views

Got this error from Keras Tuner: Number of consecutive failures excceeded the limit of 3

0 votes
0 answers
23 views

Will adding a new feature that is sum of some other features help improve the performance of tree-based models?

1 vote
1 answer
21 views

Binary Classification [Text] based on Embedding Distance?

0 votes
2 answers
16 views

how can I translate Whisper encodings to SBERT embeddings?

0 votes
0 answers
20 views

Data set dimension required for high number (thousands) of output class

1 vote
1 answer
19 views

Random forest - estimate range instead of exact value

0 votes
0 answers
17 views

How can I reduce the RMSE in my LSTM time series prediction model?

0 votes
0 answers
17 views

Classifier calibration leading to worse outcome

0 votes
1 answer
17 views

What is the dataset during testing a Variational auto-encoder?

0 votes
0 answers
17 views

General approach for "regime detection" within timeseries data

0 votes
1 answer
17 views

How do I fit huge dataset into GPU memory?

0 votes
0 answers
16 views

Scaling/Normalization again

0 votes
1 answer
16 views

How do I handle "Greater than X" in a field of integers?

0 votes
1 answer
16 views

Get multiple predictions from a knn model

0 votes
1 answer
16 views

Which modeling technique is appropriate when I have nested/hierarchical data (individual and group) but user inputs will only be at the group level?

0 votes
0 answers
15 views

Why we need encoder-decoder architectures despite we already have RNN?

0 votes
0 answers
15 views

How to deal with DataCollator and DataLoaders in Huggingface?

0 votes
0 answers
15 views

EagerTensor object has no attribute 'astype'

0 votes
1 answer
15 views

Best practices for serving user-specific large models in a web application?

0 votes
0 answers
15 views

How to do forecasting with categorical timeseries?

1 vote
0 answers
15 views

Alternatives to twitter for large daily or weekly samples for sentiment analysis

2 votes
0 answers
15 views

How Does the Reward Model in ChatGPT Calculate Losses?

0 votes
0 answers
14 views

Custom loss function in keras with class weights for each batch

1 vote
1 answer
14 views

Should I drop duplicates over features but no target

0 votes
0 answers
14 views

Which Publicly Accessible Large Language Models are Very Similar to ChatGPT?

1 vote
0 answers
13 views

Memory usage of a DNN model during inferencing

0 votes
0 answers
13 views

Should i include model.train() with Dropout in PytorchLightning

0 votes
0 answers
13 views

Online machine learning with synthetic data

0 votes
0 answers
13 views

Reinforcement Learning - What environment and algorithms should I use?

0 votes
0 answers
13 views

Can I use Deep Learning Algorithm between every two columns of excel with text data?

0 votes
1 answer
13 views

Vision Transformer ViT Parameter count

0 votes
0 answers
13 views

How to improve pytorch network to be more precise

0 votes
0 answers
13 views

Can neural network be able to convert analog timeseries to discrete timeseries

0 votes
0 answers
12 views

How to make the model fitting to the inverse-square law in Python?

0 votes
0 answers
11 views

Classification-Problem based on limited Dataset (Need keywords to search/ reading recommendations)

0 votes
0 answers
11 views

Grad-CAM for CNNs with GAP layer

0 votes
0 answers
11 views

can I use tf.keras.layers.MultiHeadAttention for image classification task?

0 votes
0 answers
11 views

How to make a predictive model using a timeseries data consisted of binary information?


Looking for more? Browse the complete list of questions, or popular tags. Help us answer unanswered questions.