• Dealing with imbalanced classes

    JUN 20, 2019 — DEEP LEARNING

    In the real world, it is not unusual to encounter datasets which are have imbalanced classes. This post discusses some strategies for dealing with such situations.

  • Mode collapse in GANs

    JAN 18, 2017 — DEEP LEARNING

    How to address mode collapse, a commonly encountered failure case for GANs where the generator learns to produce samples with extremely low variety.

  • The GAN objective, from practice to theory and back again

    DEC 21, 2016 — DEEP LEARNING

    Deciphering the GAN objective used in practice, a detour through theory, and a practical reformulation of the GAN objective in a more general form.

  • Implementing InfoGAN: easier than it seems?

    DEC 1, 2016 — DEEP LEARNING

    A look at the objective function introduced in the InfoGAN paper, and why InfoGAN really isn't that complicated to implement.

  • Neural network implementation tips and tricks

    NOV 6, 2016 — DEEP LEARNING

    Implementing neural networks can be intimidating at the start, with a daunting number of choices to make with no real sense of which option might work best. By listing my (opinionated) defaults found from experience, I hope to provide you, dear reader, with a starting point from which you can train a successful neural network.

home


© Aiden Nibali. All rights reserved.
Powered by Hugo & Goa.