Data Science Stack Exchange Community Digest

Top new questions this week:

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 …

reinforcement-learning loss-function language-model ranking loss

asked by itisyeetimetoday Score of 3

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

Question Description We are performing a lot of timeseries queries, these queries sometimes result in issues, they are usually performed through an API (Python) and sometimes result in complete …

time-series data

asked by innicoder Score of 2 answered by innicoder Score of 1

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 …

machine-learning classification decision-trees cross-validation

asked by RyRy the Fly Guy Score of 1 answered by Brian Spiering Score of 0

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 …

python tensorflow probability

asked by SkrewUGuys_Home Score of 1 answered by Brian Spiering Score of 0

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 …

random-forest xgboost auc glm

asked by user145725 Score of 1 answered by zachdj Score of 1

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 …

neural-network convolutional-neural-network visualization embeddings

asked by Zan Score of 1 answered by noe Score of 1

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 …

nlp language-model openai-gpt

asked by Qiulang Score of 1 answered by Erwan Score of 1

Greatest hits from previous weeks:

GBM vs XGBOOST? Key differences?

I am trying to understand the key differences between GBM and XGBOOST. I tried to google it, but could not find any good answers explaining the differences between the two algorithms and why xgboost …

machine-learning algorithms xgboost ensemble-modeling gbm

asked by Aman Score of 80 answered by Icyblade Score of 66

Train Accuracy vs Test Accuracy vs Confusion matrix

After I developed my predictive model using Random Forest I get the following metrics: …

python predictive-modeling accuracy confusion-matrix classifier

asked by Pedro Alves Score of 16 answered by S van Balen Score of 25

Sparse_categorical_crossentropy vs categorical_crossentropy (keras, accuracy)

Which is better for accuracy or are they the same? Of course, if you use categorical_crossentropy you use one hot encoding, and if you use …

neural-network keras loss-function encoding

asked by Master M Score of 67 answered by featuredpeow Score of 65

DeprecationWarning: The 'categorical_features' keyword is deprecated in version 0.20

I was watching Machine Learning A- Z from SuperDataScience but when I was doing below code sample: …

machine-learning python scikit-learn

asked by Navid Score of 10 answered by xYan Score of 11

The cross-entropy error function in neural networks

In the MNIST For ML Beginners they define cross-entropy as $$H_{y’} (y) := – \sum_{i} y_{i}’ \log (y_i)$$ $y_i$ is the predicted probability value for class $i$ and $y_i’$ is the true probability …

machine-learning tensorflow

asked by Martin Thoma Score of 149 answered by KT. Score of 125

How does the validation_split parameter of Keras' fit function work?

Validation-split in Keras Sequential model fit function is documented as following on keras.io/models/sequential/ : validation_split: Float between 0 and 1. Fraction of the training data …

keras data cross-validation

asked by rnso Score of 45 answered by JahKnows Score of 36

When is precision more important over recall?

Can anyone give me some examples where precision is important and some examples where recall is important?

machine-learning evaluation

asked by Rajat Score of 43 answered by SmallChess Score of 63

Can you answer these questions?

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 …

object-detection gpu

asked by Hossein Score of 1

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

Twitter, with their API, including the free tier, has been a go-to source for collecting large samples of texts expressing sentiment on various topics of interest. I just started a project in December …

sentiment-analysis twitter api

asked by ViennaMike Score of 1

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?

deep-learning neural-network pytorch deployment serialisation

asked by illan Score of 1 answered by Brian Spiering Score of 0