Posted: 29 Nov 2016 | 10:07
TensorFlow is an incredibly powerful new framework for deep learning. The “MNIST For ML Beginners” and “Deep MNIST for Experts” TensorFlow tutorials give an excellent introduction to the framework. This article acts as a follow-on tutorial which addresses the following issues:
- The above tutorials use the MNIST dataset of hand written numbers, which pre-exists in TensorFlow TFRecord format and is loaded automatically. This can be a bit mysterious if you have no experience of data format manipulation in TensorFlow.
- Since the MNIST dataset is fixed, there is little scope for experimentation through adjusting the images and network to get a feel for how to deal with particular aspects of real data.
Posted: 21 Nov 2016 | 09:59
Connor Walsh is a school pupil who joined us on a work experience placement last week. Here's his report.
I have been "working" at the EPCC offices at Edinburgh University under Eilidh Troup on a project using Python and Pygame to simulate how much an object would sink in water when you change the mass and the volume of the object.
Posted: 16 Nov 2016 | 11:41
It has been around two years since a number of us at EPCC became science, technology, engineering and mathematics (STEM) ambassadors and, as part of our outreach activities, we have maintained our membership of STEMNET (you have to do at least one STEM-related event per year).