search

tensorflow / neural-structured-learning

Training neural models with structured signals.
https://www.tensorflow.org/neural_structured_learning
Apache License 2.0
980 stars 189 forks source link

Our CVPR tutorial and its use of Neural Structured Learning #91

Closed sayakpaul closed 3 years ago

sayakpaul commented 3 years ago

Hi folks.

I wanted to let y'all know about our CVPR 2021 tutorial "Practical Adversarial Robustness in Deep Learning: Problems and Solutions (PAR)" organized by Pin-Yu Chen (IBM Research) and myself.

We made use of Neural Structured Learning in this tutorial extensively and wanted you to know about that. Code, slides, and videos of our tutorial are all available here: https://sites.google.com/view/par-2021. Was wondering if it's possible to give it a mention?

Our code is distributed as Colab Notebooks.

arjung commented 3 years ago

Hi @sayakpaul, wonderful to know about your tutorial and that you've used NSL extensively :). We're planning to create a dedicated page or a separate section of the README to document such external usage of NSL. We'd be happy to list this tutorial and related material there. Feel free to also let me know if you have given other tutorials, talks, etc, on NSL and would like to list them there.

Will keep this issue open until we have that structure in place (rough ETA 1-2 weeks).

sayakpaul commented 3 years ago

Thank you so much!

arjung commented 3 years ago

Thanks for your patience! We now have a dedicated page to document featured usage: https://github.com/tensorflow/neural-structured-learning/blob/master/usage.md, and I've already included your CVPR tutorial. Let me know if there is any other workshop/tutorial/presentation that you're aware of that should be added here. I am closing this issue now.

sayakpaul commented 3 years ago

Thanks, @arjung. The tutorial on Recognizing Multimodal Entailment looks super (especially very comprehensive). Do you folks plan to release the videos soon?

arjung commented 3 years ago

I believe so but I am not a 100% sure yet. If they become available, will definitely link them here.