Jonte DanckerinTowards Data ScienceN-HiTS — Making Deep Learning for Time Series Forecasting More EfficientA deep dive into how N-HiTS works and how you can use it·10 min read·May 30, 2024--1--1
Jonte DanckerinTowards Data ScienceN-BEATS — The First Interpretable Deep Learning Model That Worked for Time Series ForecastingAn easy-to-understand deep dive into how N-BEATS works and how you can use it.·11 min read·May 11, 2024--3--3
Jonte DanckerinTowards Data ScienceAll You Need Is Conformal PredictionAn important but easy-to-use tool for uncertainty quantification every data scientist should know.·8 min read·Apr 30, 2024--3--3
Jonte DanckerinTowards Data ScienceUncertainty Quantification and Why You Should CareHow to improve your ML model with three lines of code·8 min read·Apr 24, 2024--5--5
Jonte DanckerinTowards AIA Recipe For a Robust Model Development ProcessSix steps to reach high confidence in your model and development process5 min read·Apr 8, 2024----
Jonte DanckerinTowards AIWhy You Should Care About Business Metrics in Your Next ML ProjectBusiness metrics matter. They can kill your entire ML project.4 min read·Mar 29, 2024----
Jonte DanckerinTowards AILearning Curves: A Picture Says More Than a Thousand WordsA valuable tool to understand ML models5 min read·Mar 19, 2024--1--1
Jonte DanckerinTowards AIWhy You Should Always Start With a Baseline ModelA baseline model takes 10 % of the time to develop but gets us 90 % of the way to achieve reasonable results.4 min read·Mar 6, 2024----
Jonte DanckerThe Lifecycle of the Test SetThe integrity of the test set is crucial in evaluating model performance. We want the test set to give us an unbiased estimate of how well…2 min read·Mar 2, 2024----
Jonte DanckerinTowards AIHow to avoid common pitfalls in time series forecasting·5 min read·Feb 21, 2024----
