*Neural networks for data science* lecture 8 is out!

And it's already the last lecture! πŸ™€

What lies beyond classical supervised learning? It turns out, _way_ too many subfields!

/n
Here is my overview of everything that can happen when we have > 1 "task": fine-tuning, pre-training, meta learning, continual learning...

The slides have my personal selection of material. 😎

/n
The slides are here: sscardapane.it/assets/files/n…

All the material, as always, is here: sscardapane.it/teaching/nnds-…

/n
I have also a brand new lab session on multi-task audio classification, using #TensorFlow Hub, @huggingface Datasets, the pre-trained Wav2Vec porting by @7vasudevgupta, and a language identification dataset: 🀟

colab.research.google.com/drive/1KKusBkn…

β€’ β€’ β€’

Missing some Tweet in this thread? You can try to force a refresh
γ€€

Keep Current with Simone Scardapane

Simone Scardapane Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @s_scardapane

3 Nov
*Neural networks for data science* lecture 4 is out! πŸ‘‡

aka "here I am talking about convolutional neural networks while everyone asks me about transformers"

/n
CNNs are a great way to show how considerations about the data can guide the design of the model.

For example, only assuming locality (and not transl. invariance) we get locally-connected networks.

/n
Everything else is a pretty standard derivation of CNN ideas (stride, global pooling, receptive field, ...).

/n
Read 7 tweets
2 Aug
*Reproducible deep learning*: Time for exams!

To a practical course, a practical exam: I asked each student to include a new branch in the repository showcasing additional tools and libraries.

The result? *Everyone* loves some hyper-parameter optimization. πŸ˜„

/n
Thanks to their work, you'll find practical examples of fine-tuning parameters using @OptunaAutoML, AX (from @facebookai), @raydistributed Tune, and Auto-PyTorch and Talos coming soon.

So many ideas for next year! πŸ˜›

github.com/sscardapane/re…

/n
You will also find additional exercises on:

- Serving the model with TorchServe;
- Managing experiments with @DVCorg 2.0;
- Set up cron jobs for re-training.

BTW, if you'd like to add something, feel free to contact me or open a pull request. πŸ™‚

github.com/sscardapane/re…

/n
Read 4 tweets
16 Jun
*Score-based diffusion models*

An emerging approach in generative modelling that is gathering more and more attention.

If you are interested, I collected some introductive material and thoughts in a small thread. πŸ‘‡

Feel free to weigh in with additional material!

/n
An amazing property of diffusion models is simplicity.

You define a probabilistic chain that gradually "noise" the input image until only white noise remains.

Then, generation is done by learning to reverse this chain. In many cases, the two directions have similar form.

/n
The starting point for diffusion models is probably "Deep Unsupervised Learning using Nonequilibrium Thermodynamics" by @jaschasd Weiss @niru_m @SuryaGanguli

Classic paper, definitely worth reading: arxiv.org/abs/1503.03585

/n
Read 13 tweets
14 Jun
*LocoProp: Enhancing BackProp via Local Loss Optimization*
by @esiamid @_arohan_ & Warmuth

Interesting approach to bridge the gap between first-order, second-order, and "local" optimization approaches. πŸ‘‡

/n Image
The key idea is to use a single GD step to define auxiliary local targets for each layer, either at the level of pre- or post-activations.

Then, optimization is done by solving local "matching" problems wrt these new variables.

/n Image
What is intriguing is that the framework interpolates between multiple scenarios: first solution step is the original GD, while closed-form solution (in one case) is similar to a pre-conditioned GD model. Optimization is "local" in the sense that it decouples across layers.

/n Image
Read 4 tweets
11 May
*Reproducible Deep Learning*

The first two exercises are out!

We start quick and easily, with some simple manipulation on Git branches, scripting, audio classification, and configuration with @Hydra_Framework.

Small thread with all information πŸ™ƒ /n
Reproducibility is associated to production environments and MLOps, but it is a major concern today also in the research community.

My biased introduction to the issue is here: docs.google.com/presentation/d…
The local setup is on the repository: github.com/sscardapane/re…

The use case for the course is a small audio classification model trained on event detection with the awesome @PyTorchLightnin library.

Feel free to check the notebook if you are unfamiliar with the task. /n
Read 8 tweets
11 May
*Weisfeiler and Lehman Go Topological*

Fantastic #ICLR2021 paper by @CristianBodnar @ffabffrasca @wangyg85 @kneppkatt MontΓΊfar @pl219_Cambridge @mmbronstein

Graph networks are limited to pairwise interactions. How to include higher-order components?

Read more below πŸ‘‡ /n
The paper considers simplicial complexes, nice mathematical objects where having a certain component (e.g., a 3-way interaction in the graph) means also having all the lower level interactions (e.g., all pairwise interactions between the 3 objects). /n
Simplicial complexes have many notions of "adjacency" (four in total), considering lower- and upper- interactions.

They first propose an extension of the Weisfeiler-Lehman test that includes all four of them, showing it is slightly more powerful than standard WL. /n
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(