Ivan Zhang

Canada Contact Info
2K followers 500+ connections

Join to view profile

Activity

Join now to see all activity

Experience & Education

  • Cohere

View Ivan’s full experience

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Publications

  • Targeted Dropout

    NIPS CDNNRIA Workshop

    Neural networks are extremely flexible models due to their large number of parameters, which is beneficial for learning, but also highly redundant. This makes it possible to compress neural networks without having a drastic effect on performance. We introduce targeted dropout, a strategy for post hoc pruning of neural network weights and units that builds the pruning mechanism directly into learning. At each weight update, targeted dropout selects a candidate set for pruning using a simple…

    Neural networks are extremely flexible models due to their large number of parameters, which is beneficial for learning, but also highly redundant. This makes it possible to compress neural networks without having a drastic effect on performance. We introduce targeted dropout, a strategy for post hoc pruning of neural network weights and units that builds the pruning mechanism directly into learning. At each weight update, targeted dropout selects a candidate set for pruning using a simple selection criterion, and then stochastically prunes the network via dropout applied to this set. The resulting network learns to be explicitly robust to pruning, comparing favourably to more complicated regularization schemes while at the same time being extremely simple to implement, and easy to tune.

    Other authors
    See publication

  • Unsupervised Cipher Cracking Using Discrete GANs

    Arxiv

    This work details CipherGAN, an architecture inspired by CycleGAN used for inferring the underlying cipher mapping given banks of unpaired ciphertext and plaintext. We demonstrate that CipherGAN is capable of cracking language data enciphered using shift and Vigenere ciphers to a high degree of fidelity and for vocabularies much larger than previously achieved. We present how CycleGAN can be made compatible with discrete data and train in a stable way. We then prove that the technique used in…

    This work details CipherGAN, an architecture inspired by CycleGAN used for inferring the underlying cipher mapping given banks of unpaired ciphertext and plaintext. We demonstrate that CipherGAN is capable of cracking language data enciphered using shift and Vigenere ciphers to a high degree of fidelity and for vocabularies much larger than previously achieved. We present how CycleGAN can be made compatible with discrete data and train in a stable way. We then prove that the technique used in CipherGAN avoids the common problem of uninformative discrimination associated with GANs applied to discrete data.

    Other authors
    See publication

More activity by Ivan

View Ivan’s full profile

  • See who you know in common
  • Get introduced
  • Contact Ivan directly
Join to view full profile

People also viewed

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Ivan Zhang in Canada

28 others named Ivan Zhang in Canada are on LinkedIn

See others named Ivan Zhang

Add new skills with these courses

See all courses