Artificiality Bites đź’Š Issue #47
Hello Human! This is a new issue from my weekly newsletter, holding a tiny compilation made of interesting articles from last week, projects, tutorials and tools; all related to Data, Artificial Intelligence and adjacent topics. अपने ŕ¤ŕĄ‹ŕ¤śŕ¤¨ का आनंद लें!
đź“ť Interesting publications this week
- Alien Dreams: An Emerging Art Scene
18'
A recapitulation on the early milestones in the evolution of CLIP-based generative art.
- ModelOps — AI Model Operationalization for the Enterprise
13'
This article take a dive into ModelOps and the technologies that support this effort, with some use cases where it makes a difference. - Double Machine Learning for causal inference
9'
How Double Machine Learning for causal inference works, from the theoretical foundations to an example of application. - Data Strata
12'
This essay looks into the matters of neutrality and transparency in data visualization design.
đź’ˇ Projects
- Bird Sound Classifier on the Edge
7'
The project attempts to recognize different bird calls by continuously listening to the audio using Arduino Nano.
🔧 Tutorials
- Semantic Search: Measuring Meaning From Jaccard to Bert
50'
This article covers a few of the most powerful techniques for building effective search engines, focusing specifically on semantic search and showing how they work, what they’re good at, and how we can implement them ourselves. - The Auto-Sommelier — How to Implement HuggingFace Transformers and Build a Search Engine
11'
How to use the HuggingFace Transformers library, the Non-Metric Space Library, and the Dash library to build a wine recommender based on a user's query.
📦 Repositories
- google-research/deeplab2
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks, including semantic segmentation, instance segmentation, panoptic segmentation or depth estimation.
- Netflix/nf-data-explorer
The Netflix Data Explorer tool allows users to explore data stored in several popular datastores (currently Cassandra, Dynomite, and Redis). Read more on Netflix Tech Blog. - robustness-gym/meerkat
Meerkat makes it easier for ML practitioners to interact with high-dimensional, multi-modal data. It provides simple abstractions for data inspection, model evaluation and model training supported by efficient and robust IO under the hood. Read more here. - DAGsHub/fds
FDS (Fast Data Science) is a CLI for Data Scientists to version control data and code at once, by conveniently wrapping Git and DVC.
🎓 Courses / Events
- Machine Learning for Beginners — A Curriculum
Microsoft offer a 12-week, 24-lesson curriculum all about classic Machine Learning using primarily Scikit-learn and avoiding deep learning.
🚀 Extra bits
đź‘‹ See you next week!