Daniel AngelovinTowards Data ScienceMaking models more robust more efficientlyDeploying ML models to the real world is prone to uncover domain coverage issues. Let’s robustify the models by generating unseen data!7 min read·Jul 23, 2021--1--1
Daniel AngelovinTowards Data ScienceWhy don’t we test machine learning like we test software?Let’s make ML models more robust by taking inspiration from modern software testing! A new way to confidently improve your models.10 min read·Jun 24, 2021----
Daniel AngelovVisual explanation of tensor operationsWhen you start your machine learning journey, you are very early on hit by new terminology. So let’s see what are tensors and what can we…4 min read·Apr 5, 2021----
Daniel AngelovFree tools to visualize your computational graphCreating neural networks often involves debugging the structure, sequence and loss functions used in different parts of the model. What is…3 min read·Mar 19, 2021----
Daniel AngelovWhat actually happens when you transfer a model to a custom dataset?See visually what needs to be altered in the model and how it impacts further training.6 min read·Mar 11, 2021----