Bjørn-Jostein Singstad·May 29, 2025Understanding the Bias-Variance Tradeoff in Machine LearningWhy your model isn’t performing well — and how to fix it
Bjørn-Jostein Singstad·May 29, 2025Stop Paying for QR Code Subscriptions — Use Canva for Free InsteadWhy You Shouldn’t Be Paying Monthly Fees for Something as Simple as a QR Code
Bjørn-Jostein Singstad·Aug 29, 2024LIME 1D Convolutional Neural Network ExplainerHow to squeeze a CNN explanation out of a LIME Recurrent Tabular Explainer
InIntuitionbyBjørn-Jostein Singstad·Apr 20, 2023The False-Positive paradox explained in an easy wayThe concept of false-positive paradox highlights the misleading nature of a diagnostic test that exhibits high sensitivity and specificity…
Bjørn-Jostein Singstad·Feb 8, 2023Great work! Have you considered using GAN to produce the raw ECG waveform also?A response icon1A response icon1
Bjørn-Jostein Singstad·Feb 6, 2023How to train a CNN using tf.GradientTapeA simple practical example of how to use TensorFlow's GradientTape to train a convolutional neural network.
Bjørn-Jostein Singstad·Jan 23, 2023What's your cardiovascular age?In this article, I show how a Convolutional Neural Network can be used to predict a person's age based on the person's ECG
Bjørn-Jostein Singstad·Mar 15, 2022ECHO2022Machine Learning challenge: Predict cardiac ejection fraction from echocardiogram loops
Bjørn-Jostein Singstad·Jan 17, 2022Hi. Great article, but your Sigmoid curves in the last plot is shifted towards the wrong direction.The code block below shows how this can be proved in Python. In this code, we consider one single neuron with one input + bias. The input…A response icon1A response icon1
InTDS ArchivebyBjørn-Jostein Singstad·Jan 14, 2022NumPy reshape can break your heartNumPy reshape may not literally break your heart, but it can make unintentional changes to time-series like e.g electrocardiograms (ECG)…