Questions tagged [mlops]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
3 votes
2 answers

Why business experts should prefer state-of-the-art deep neural networks over simpler models? [closed]

I have encountered this pattern for a long time (5+ years). So many professionals come with an interesting domain-specific problem, and they demand using state-of-the-art deep learning models: take it ...
  • 211
0 votes
1 answer

How to filter out class for which the model has not been trained in ml web app?

I have developed an python based ml web app. It gives details of the book from a image of book cover. Problem: When I upload the book cover image then it works but when i click image of any random ...
-1 votes
1 answer

When is it better to utilize machine learning over heuristics?

I learned that 87% of machine learning projects fail due to these five pitfalls: the scope of the project is too big; the project’s scope increased in size as the project progressed—e.g., scope creep;...
0 votes
0 answers

Best FAANG Publications on Software Development Aspects of Model Training, Deployment and Monitoring

I recently came upon this good reference from Microsoft on software development aspects of deep learning models and their operationalisation. The paper itself is based mostly on Microsoft's internal ...
  • 111
0 votes
0 answers

Calculation of the out-of distribution (OOD) and in-distribution (ID) performance (in distrbutional shifts)

Within my work I have collected a lot of data with a question on how to evaluate my datasets properly to give a more data-centric view. What I have come across is the 'Wilds' paper which can be found ...
0 votes
1 answer

How can batch prediction make drift monitoring easier than online prediction?

In this video, I learned that drift monitoring would be easier in batch prediction than that in online prediction: But I don't know why and I cannot find any information about it googling. In my ...
2 votes
2 answers

How will MLOps and lifelong learning be complementary?

According to [1], in MLOps, continuous training is a new property, unique to ML systems, that's concerned with automatically retraining and serving the models. While lifelong/incremental learning ...