The wrong batch size is all it takes
How different batch sizes influence the training process of neural networks using gradient descent.
Overfitting and Underfitting with Learning Curves
An introduction to two fundamental concepts in machine learning through the lens of learning curves.
When accuracy doesn't help
An introduction to precision, recall, and f1-score metrics to measure a machine learning model's performance.
Confusion Matrix
One of the simplest and most popular tools to analyze the performance of a classification model.
Early Stopping
One of the most effective, easy-to-implement regularization techniques when training machine learning models.
Active Learning
A learning technique to build better-performing machine learning models using fewer training labels.
Autoencoders
A learning technique to represent data efficiently using neural networks.
Adversarial Validation
A clever technique to help you understand why your machine learning model is not performing well on your test dataset.
Test-time Augmentation
How you can use Test-Time Augmentation to make better predictions with your machine learning model.