Machine Learning

Step-by-step

Step by step recurrent neural network inference with Keras

We often use recurrent neural network architectures for use cases such as streaming, where we make a new prediction each time new information arrives. It’s common to give it a long context each time, which repeats work and is therefore computationally wasteful. In this blog post, I will illustrate multiple ways to perform inference step

Step by step recurrent neural network inference with Keras Read More »

How to implement the K-means algorithm in Tensorflow

The K-means algorithm is a simple clustering algorithm. It is an unsupervised learning algorithm, therefore it automatically finds structure in unordered data. Since TensorFlow does not have a native implementation, it’s useful to know the tips and tricks to implement K-means. I’m hoping to use K-means in an upcoming post, so I want to explain

How to implement the K-means algorithm in Tensorflow Read More »

Creating a custom training loop in tensorflow

Sticking to the sequential model limits the freedom you have with regards to creating models in Tensorflow. In this post, I’ll start by showing a simple sequential model. I’ll then convert it into a functional model. Finally, I’ll use GradientTape to calculate all gradients and control the full train loop, all to improve the possibilities

Creating a custom training loop in tensorflow Read More »