Daniel Angelov

Published in
TDS Archive

Making models more robust more efficiently

Deploying ML models to the real world is prone to uncover domain coverage issues. Let’s robustify the models by generating unseen data!

Jul 23, 2021

Making models more robust more efficiently

Jul 23, 2021

Published in
TDS Archive

Why 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.

Jun 24, 2021

Why don’t we test machine learning like we test software?

Jun 24, 2021

Get an email whenever Daniel Angelov publishes.

By signing up, you will create a Medium account if you don’t already have one. Review our Privacy Policy for more information about our privacy practices.

Medium sent you an email at to complete your subscription.

Visual explanation of tensor operations

When 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…

Apr 5, 2021

Apr 5, 2021

Free tools to visualize your computational graph

Creating neural networks often involves debugging the structure, sequence and loss functions used in different parts of the model. What is…

Mar 19, 2021

Free tools to visualize your computational graph

Mar 19, 2021

What 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.

Mar 11, 2021

What actually happens when you transfer a model to a custom dataset?

Mar 11, 2021