Published on

FOSSASIA 2016 : Deep Learning Workshop


I recently lead a 2 hour workshop at FOSSASIA 2016 in Singapore.

This workshop was hands-on : After a brief background on deep learning, participants started quickly, interacting with ConvNet.js models. But this on-line portion was partly to allow everyone enough time to get the ~1Gb VirtualBox "appliance" created for the event installed on their laptops. Fortunately, over 90% of the people who came already had VirtualBox installed, which was a huge relief.

Once everyone was up-to-speed tools-wise, the workshop then progressed through a series of Jupyter (fka iPython) notebooks, ranging from Theano basics, through MNIST, to ImageNet networks (pretrained models of both GoogLeNet and Inception-v3 were included in the VM).

Then, for the last half-hour, we went over two interesting applications : One with a 'commercial' angle (transfer learning), the other 'art' (using style-transfer).

Naturally, this being a FOSS event, all the source is available on GitHub - if you have questions on the software, please leave an 'issue' there.