- Exploring the SwAV Method - Jul 9, 2021.
This post discusses the SwAV (Swapping Assignments between multiple Views of the same image) method from the paper “Unsupervised Learning of Visual Features by Contrasting Cluster Assignments” by M. Caron et al.
Feature Extraction, Image Classification, Modeling, Training
- A Key Missing Part of the Machine Learning Stack - Apr 20, 2020.
With many organizations having machine learning models running in production, some are discovering that inefficiencies exists in the first step of the process: feature definition and extraction. Robust feature management is now being realized as a key missing part of the ML stack, and improving it by applying standard software development practices is gaining attention.
Feature Engineering, Feature Extraction, Feature Store, Machine Learning
- The Hitchhiker’s Guide to Feature Extraction - Jun 3, 2019.
Check out this collection of tricks and code for Kaggle and everyday work.
Feature Engineering, Feature Extraction, Feature Selection, Kaggle, Python
- A Quick Guide to Feature Engineering - Feb 11, 2019.
Feature engineering plays a key role in machine learning, data mining, and data analytics. This article provides a general definition for feature engineering, together with an overview of the major issues, approaches, and challenges of the field.
Feature Engineering, Feature Extraction, Feature Selection
- Making Machine Learning Simple - Mar 20, 2018.
Learn how to build better models with support for multiple data sources and feature extraction at scale, simplify operations with on-demand cluster management, and more.
Apache Spark, Databricks, Feature Extraction, Machine Learning
- Introduction to Natural Language Processing, Part 1: Lexical Units - Feb 16, 2017.
This series explores core concepts of natural language processing, starting with an introduction to the field and explaining how to identify lexical units as a part of data preprocessing.
Data Preprocessing, Datascience.com, Feature Extraction, Natural Language Processing, NLP, Tokenization
- 3 practical thoughts on why deep learning performs so well - Feb 3, 2017.
Why does Deep Learning perform better than other machine learning methods? We offer 3 reasons: integration of integration of feature extraction within the training process, collection of very large data sets, and technology development.
Big Data, Convolutional Neural Networks, Deep Learning, Deep Neural Network, Feature Extraction, Recurrent Neural Networks
- Urban Sound Classification with Neural Networks in Tensorflow - Sep 12, 2016.
This post discuss techniques of feature extraction from sound in Python using open source library Librosa and implements a Neural Network in Tensorflow to categories urban sounds, including car horns, children playing, dogs bark, and more.
Pages: 1 2
Deep Learning, Feature Extraction, Machine Learning, Neural Networks, TensorFlow
- Doing Data Science: A Kaggle Walkthrough Part 4 – Data Transformation and Feature Extraction - Jun 10, 2016.
Part 4 of this fantastic 6 part series covering the process of data science, and its application to a Kaggle competition, focuses on feature extraction and data transformation.
Pages: 1 2
Feature Extraction, Kaggle, Python
- scikit-feature: Open-Source Feature Selection Repository in Python - Mar 3, 2016.
scikit-feature is an open-source feature selection repository in python, with around 40 popular algorithms in feature selection research. It is developed by Data Mining and Machine Learning Lab at Arizona State University.
Data Mining, Data Science, Feature Extraction, Feature Selection, Machine Learning, Python
- The Data Science Machine, or ‘How To Engineer Feature Engineering’ - Oct 22, 2015.
MIT researchers have developed what they refer to as the Data Science Machine, which combines feature engineering and an end-to-end data science pipeline into a system that beats nearly 70% of humans in competitions. Is this game-changing?
Automated, Data Science, Feature Engineering, Feature Extraction, MIT
- 3 Things About Data Science You Won’t Find In Books - May 11, 2015.
There are many courses on Data Science that teach the latest logistic regression or deep learning methods, but what happens in practice? Data Scientist shares his main practical insights that are not taught in universities.
Pages: 1 2
Cross-validation, Data Preparation, Data Science, Feature Engineering, Feature Extraction, Overfitting