a blog about what's cool to me
Dimensionality reduction is useful in compressing the representation of your data. In my last post, how not to reduce dimensionality for clustering, I show a neural network that reduces the 784 dimensions of the MNIST dataset into 3, which are constrained by the k-means algorithm to capture the essence of the data. This week we’ll […]
Reduce MNIST dimensionality using autoencoders Read More »
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 »
Keras offers a large amount of flexibility to its dense layers. In this more advanced post, I’ll illustrate this and rationalise why it happens. If you are unfamiliar with shapes or the way Keras handles them, my posts Shapes – an introduction and A closer look at shapes might help. Let’s dive right in with
on the flexibility of dense layers in Keras Read More »
Understanding shapes is an integral part of demystifying how data gets passed around in your model. If you are unfamiliar with shapes, reading my previous post, Shapes – an introduction, might help. In this post, I’ll explore how Tensorflow expects to receive data, and hopefully provide a better intuition for how to conceptualise your data
A closer look at shapes Read More »