tags: ML

Neural Network Learning

I was trying to explain how a neural learns to perform certain tasks by performing a series of transformations so decided to put a little notebook together to visualise this process. You can see the notebook here and the html version here.

Using Google Colab for Machine Learning Development

Due to work restrictions, I have been using Tensorflow CPU version for all of my development. However, with model training taking several hours, I have been fininding the development cycle a bit slow. I was therefore on the lookout for some GPU machines that I could try and see what speedup I got. Google Colab is a great free resource for development and even model training on GPUs (and TPUs). I have been using Tensorflow 2.

Read more →

Keras Acc Metric

I have been developing a machine learning model in Tensorflow 2.0, but because I need to have some custom functionality I am taking a more manual approach instead of full Keras API e.g. see https://www.tensorflow.org/tutorials/quickstart/advanced . One thing that was not clear to me was what algorithm does Keras use when you pass in the option metric=['acc'] to model.compile(). It turns out Keras does clever things and works out the appropriate metric based on your data.

Read more →

Omar Jamil

Exeter, England
Email me

I am a Senior Scientist at the UK Met Office, using machine learning to develop and improve the physics in the weather and climate model. I specialise in radiative transfer with remote sensing applications. In short, I create mathematical and physics models to make sense of data.