Machine learning means that a computer can learn from experience without being specifically programmed. But, is the computer learning the right things?

Gears, servos, and circuits, oh my! So, many things go into a Transformer! So many things to examine! Oh...wait...that’s the wrong Transformer.

When you need to go faster, but RNNs cannot keep up. Whom do you call? Transformers, of course.

Let’s take a step back and examine a machine learning architecture that has become the go-to for image recognition and computer vision.

Memory is essential to NTMs. So, understanding NTMs’ memory addressing system is a must.

We have added attention and gates to our neural networks. Now, let’s revolutionize machine learning with memory.

LSTMs fix vanishing and exploding gradients, but LSTMs are not the only architectures that do that.

LSTMs are widely used in machine learning now. What are they? How do they work?

Backpropagation is so commonplace in neural network training that it is easy to take it for granted. But what is it?

Applying the attention principle to more tasks meant that the attention mechanism had to be modified.

The attention mechanism has become widespread in neural NLP modeling, but where did it come from?