- Metric Matters, Part 1: Evaluating Classification Models - Mar 16, 2021.
You have many options when choosing metrics for evaluating your machine learning models. Select the right one for your situation with this guide that considers metrics for classification models.
- Evaluating Deep Learning Models: The Confusion Matrix, Accuracy, Precision, and Recall - Feb 19, 2021.
This tutorial discusses the confusion matrix, and how the precision, recall and accuracy are calculated, and how they relate to evaluating deep learning models.
- Can you trust AutoML? - Dec 23, 2020.
Automated Machine Learning, or AutoML, tries hundreds or even thousands of different ML pipelines to deliver models that often beat the experts and win competitions. But, is this the ultimate goal? Can a model developed with this approach be trusted without guarantees of predictive performance? The issue of overfitting must be closely considered because these methods can lead to overestimation -- and the Winner's Curse.
- KDnuggets™ News 20:n37, Sep 30: Introduction to Time Series Analysis in Python; How To Improve Machine Learning Model Accuracy - Sep 30, 2020.
Learn how to work with time series in Python; Tips for improving Machine Learning model accuracy from 80% to over 90%; Geographical Plots with Python; Best methods for making Python programs blazingly fast; Read a complete guide to PyTorch; KDD Best Paper Awards and more.
- How I Consistently Improve My Machine Learning Models From 80% to Over 90% Accuracy - Sep 23, 2020.
Data science work typically requires a big lift near the end to increase the accuracy of any model developed. These five recommendations will help improve your machine learning models and help your projects reach their target goals.
- A Deep Learning Dream: Accuracy and Interpretability in a Single Model - Sep 7, 2020.
IBM Research believes that you can improve the accuracy of interpretable models with knowledge learned in pre-trained models.
- How to Evaluate the Performance of Your Machine Learning Model - Sep 3, 2020.
You can train your supervised machine learning models all day long, but unless you evaluate its performance, you can never know if your model is useful. This detailed discussion reviews the various performance metrics you must consider, and offers intuitive explanations for what they mean and how they work.
- Achieving Accuracy with your Training Dataset - Mar 5, 2020.
How do we make sure our training data is more accurate than the rest? Partners like Supahands eliminate the headache that comes with labeling work by providing end-to-end managed labeling solutions, completed by a fully managed workforce that is trained to work on your model specifics.
- Idiot’s Guide to Precision, Recall, and Confusion Matrix - Jan 13, 2020.
Building Machine Learning models is fun, but making sure we build the best ones is what makes a difference. Follow this quick guide to appreciate how to effectively evaluate a classification model, especially for projects where accuracy alone is not enough.
- Accuracy vs Speed – what Data Scientists can learn from Search - Jan 2, 2020.
Delivering accurate insights is the core function of any data scientist. Navigating the development road toward this goal can sometimes be tricky, especially when cross-collaboration is required, and these lessons learned from building a search application will help you negotiate the demands between accuracy and speed.
- What is the most important question for Data Science (and Digital Transformation) - Dec 31, 2019.
With so many buzzwords surrounding AI and machine learning, understanding which can bring business value and which are best left in the lab to mature is difficult. While machine learning offers significant power in driving digital transformations, a business must start with the right questions and leave the math to the development teams.
- Accuracy Fallacy: The Media’s Coverage of AI Is Bogus - Dec 6, 2019.
Such as the gross exaggerations Stanford researchers broadcasted about their infamous "AI gaydar" project, there exists a prevalent "accuracy fallacy" in relation to AI from the media. Find out more about how the press constantly misleads the public into believing that machine learning can reliably predict psychosis, heart attacks, sexuality, and much more.
- Machine Learning 101: The What, Why, and How of Weighting - Nov 26, 2019.
Weighting is a technique for improving models. In this article, learn more about what weighting is, why you should (and shouldn’t) use it, and how to choose optimal weights to minimize business costs.
- Transfer Learning Made Easy: Coding a Powerful Technique - Nov 13, 2019.
While the revolution of deep learning now impacts our daily lives, these networks are expensive. Approaches in transfer learning promise to ease this burden by enabling the re-use of trained models -- and this hands-on tutorial will walk you through a transfer learning technique you can run on your laptop.
- This New Google Technique Help Us Understand How Neural Networks are Thinking - Jul 24, 2019.
Recently, researchers from the Google Brain team published a paper proposing a new method called Concept Activation Vectors (CAVs) that takes a new angle to the interpretability of deep learning models.
- 5 Things to Know About Machine Learning - Mar 7, 2018.
This post will point out 5 thing to know about machine learning, 5 things which you may not know, may not have been aware of, or may have once known and now forgotten.
- The Costs of Misclassifications - Dec 14, 2016.
Importance of correct classification and hazards of misclassification are subjective or we can say varies on case-to-case. Lets see how cost of misclassification is measured from monetary perspective.
- The Best Metric to Measure Accuracy of Classification Models - Dec 7, 2016.
Measuring accuracy of model for a classification problem (categorical output) is complex and time consuming compared to regression problems (continuous output). Let’s understand key testing metrics with example, for a classification problem.
Pages: 1 2
- Interpretability over Accuracy - Aug 25, 2016.
If researchers can’t understand a provided answer, it is not viable. They can’t write about techniques they don’t understand beyond “Here are the numbers. Look how pretty my model is.” Good research, that ain’t.
- The Machine Learning Problem of The Next Decade - Feb 26, 2016.
How can businesses integrate imperfect machine-learning algorithms into their workflow?
Pages: 1 2
- New Tools Predict Markets with 99.9% certainty - Feb 8, 2016.
Predicting financial markets is a relatively new field of of research, it is cross-disciplinary, it is difficult and requires some insight into trading, computational linguistics, behavioral finance, pattern recognition, and learning models.
- How to Balance the Five Analytic Dimensions - Sep 3, 2015.
When developing a solution one has to consider data complexity, speed, analytic complexity, accuracy & precision, and data size. It is not possible to best in all categories, but it is necessary to understand the trade-offs.
- How to Lead a Data Science Contest without Reading the Data - May 17, 2015.
We examine a “wacky” boosting method that lets you climb the public leaderboard without even looking at the data . But there is a catch, so read on before trying to win Kaggle competitions with this approach.
- Failing Optimally – Data Science’s Measurement Problem - Mar 4, 2015.
Data science has a measurement problem. Simple metrics may not address complex situations. But complex metrics present myriad problems.
- Top stories in February: 3 Ways to test the accuracy; Exclusive Interview with Yann LeCun; One Page R - Mar 6, 2014.
3 Ways to Test the Accuracy of Your Predictive Models; KDnuggets Exclusive: Interview with Yann LeCun, One Page R: A Survival Guide to Data Science with R; Cartoon: Data Scientist Valentine Day Prediction.
- KDnuggets 14:n04, Text Analytics slow takeoff; Data Scientist Valentine Day; 3 Ways to test model accuracy - Feb 19, 2014.
Latest analytics/data mining news, including surprisingly little change in Text Analytics use, Data Scientist Valentine Day, and Features (7) | News (10) | Software (2) | Webcasts (2) | Courses (2) | Meetings (2) | Jobs (10) | Academic (4) | Publications (6) | Tweets (6) | CFP (14) .
- Top stories for Feb 9-15: Cartoon: Data Scientist Valentine Day Prediction; 3 Ways to Test the Accuracy of Predictive Models - Feb 16, 2014.
Cartoon: Data Scientist Valentine Day Prediction; 3 Ways to Test the Accuracy of Your Predictive Models; One Page R: A Survival Guide to Data Science with R; Book: Mining of Massive Datasets, 2nd Edition, free download.
- Top KDnuggets tweets, Feb 7-9: 3 ways to test predictive models; 90% of top-paying IT jobs Big Data related - Feb 10, 2014.
3 ways to test Predictive Models accuracy; 90% of top-paying IT jobs are related to #BigData, R; 10 Emerging Analytics Startups in India ; CMSR Data Miner/Rule-Engine Software - free academic use.
- Top stories for Feb 2-8: Predicting Sochi Olympics Medals; 3 Ways to Test Predictive Models - Feb 10, 2014.
Using Data Mining to Predict the Winter Olympics Medal Counts in Sochi; Top stories in January: Tutorial: Data Science in Python; 3 Ways to Test the Accuracy of Your Predictive Models; Viewpoint: Statistical Data Science, The Data Analysis Side.