mlpack  blog
Implementing Essential Deep Learning Modules - Week 7

Implementing Essential Deep Learning Modules - Week 7

Shikhar Jaiswal, 02 July 2018

We have formally entered a streak of productive weeks! The WGAN PR is now complete and under review, and should be ready to merge anytime next week. We have totally refactored the GAN module according to SFINAE + enable_if<> paradigm, allowing us to choose the variant of GAN at compile time.

With the above changes, we have further reduced the training time to under ~7 hours with all the variants! We tested our implementations, again on the full 70,000 image MNIST dataset, and obtained the following results:

Standard GAN




We're still planning out the optimal startegy for implementing DualOptimizer class. Thankfully, Marcus has offered his help (as always) regarding the same. We have also planned to complete the RBM and Spike and Slab RBM work left over from Kris' GSoC last year. We have been very fortunate to cover a lot up until now, and probably we can cover a lot more this month as well.