List: ML-new-and-useful | Curated by Julio Cárdenas-Rodríguez

Feb 19, 2024
17 stories
ML-new-and-useful
In
TDS Archive
by
Jacky Kaub
The Biggest Weakness Of Boosting TreesWhy distribution drifts can really hurt your models
Feb 12, 2024
10
Feb 12, 2024
10
Düzgün İlaslan
How to serve Machine Learning model using FastAPI+MLFlow+MINIO+MySQLThis is the easy way to serve ML models with FastAPI
Jun 4, 2023
3
Jun 4, 2023
3
Rayyan Shaikh
Mastering BERT: A Comprehensive Guide from Beginner to Advanced in Natural Language Processing…Introduction: A Guide to Unlocking BERT: From Beginner to Expert
Aug 26, 2023
20
Aug 26, 2023
20
In
Towards AI
by
Bex T.
Forget PIP, Conda, requirements.txt! Use Poetry Instead And Thank Me LaterPain-free dependency management is finally here
Jun 24, 2023
26
Jun 24, 2023
26
In
Becoming Human: Artificial Intelligence Magazine
by
Lak Lakshmanan
No, You Don’t Need MLOpsKeep It Simple: the complexity of full MLOps is rarely needed
Sep 18, 2022
6
Sep 18, 2022
6
In
Snowflake Builders Blog: Data Engineers, App Developers, AI/ML, & Data Science
by
Phani Raj
Migrating from PySpark to Snowpark Python Series — Part 1Dated: June 2022
Jun 9, 2022
2
Jun 9, 2022
2
In
Becoming Human: Artificial Intelligence Magazine
by
Kovendhan Venugopal
Mathematical Introduction to GloVe Word EmbeddingTopics covered in this article are:
May 8, 2021
1
May 8, 2021
1
In
TDS Archive
by
Edwin Tan
How to Prepare Scikit-Learn Models for ProductionServe scikit-learn models with FastAPI and Docker
Sep 27, 2022
3
Sep 27, 2022
3
In
TDS Archive
by
Vinay Kudari
SQLAlchemy — Python TutorialWe often encounter data as Relational Databases. To work with them we generally would need to write raw SQL queries, pass them to the…
Aug 23, 2018
16
Aug 23, 2018
16
Liam Roberts
Stop Pickling your ML Models. Use ONNX instead!So the first thing I will say is that there is nothing inherently wrong with pickling your models. It’s just that it imposes several…
Aug 31, 2022
2
Aug 31, 2022
2
 This story is no longer available
In
The Prefect Blog
by
Khuyen Tran
Orchestrate Your Data Science Project with Prefect 2.0Make Your Data Science Pipeline Resilient Against Failures
Jun 29, 2022
1
Jun 29, 2022
1
In
TDS Archive
by
Keith McNulty
Quarto: A Game Changer For Rendering Jupyter NotebooksWith Quarto, your Jupyter notebooks can now be easily published into various professional formats
Aug 8, 2022
3
Aug 8, 2022
3
In
Data For Science
by
Bruno Gonçalves
Causal Inference — Part XV — MediationThis is the fifteenth post on the series we work our way through “Causal Inference In Statistics” a nice Primer co-authored by Judea Pearl…
Feb 14, 2021
Feb 14, 2021
In
TDS Archive
by
Kurtis Pykes
Normalized Discounted Cumulative GainA Metric for Evaluating Recommendation Engines
Aug 8, 2020
3
Aug 8, 2020
3
Tamara Alexandra Cucumides
Learning-to-rank with LightGBM (Code example in python)LightGBM: brief description and usage
Jan 22, 2020
6
Jan 22, 2020
6
In
Towards AI
by
Michał Oleszak
Estimating Model Performance without Ground TruthIt’s possible, as long as you keep your probabilities calibrated
May 12, 2022
2
May 12, 2022
2