​​Making Animoji or any other 3D avatar more human-like

#Facebook researchers suggested an approach for more precise facial and gaze expression tracking.

Review: https://syncedreview.com/2020/07/07/facebook-introduces-integrated-eye-face-model-for-3d-immersion-in-remote-communication/
Paper: https://research.fb.com/wp-content/uploads/2020/06/The-Eyes-Have-It-An-Integrated-Eye-and-Face-Model-for-Photorealistic-Facial-Animation.pdf

#eyetracking #cv #dl #3davatar #videolearning #facerecognition

Soon we will give a try to certain solution which will allow commenting on the posts in this channel.

Therefore, we will at first release the Ultimate Post on #wheretostart with Data Science, describing various entry points, books and courses. We want to provide extensive and thorough manual (just check out the name we chose), so we would be grateful if you can submit any resourses on getting starting with DS (any sphere) through our bot @opendatasciencebot (make sure you add your username, so we can reach you back)

You are most welcome to share:

Favourite books, youtube playlists, courses or even success stories.

​​A new SOTA on voice separation model that distinguishes multiple speakers simultaneously

Pandemic given a sufficient rise to new technologies covering voice communication. Noise cancelling is required more than ever and now #Facebook introduced a new method for separating as many as five voices speaking simultaneously into a single microphone. It pushes state of the art on multiple benchmarks, including ones with challenging noise and reverberations.

Blogpost: https://ai.facebook.com/blog/a-new-state-of-the-art-voice-separation-model-that-distinguishes-multiple-speakers-simultaneously
Paper: https://arxiv.org/pdf/2003.01531.pdf

#SOTA #FacebookAI #voicerecognition #soundlearning #DL

Soon we will share verified list of mostly free and open cources to learn data science disciplines.

Knowledge Graphs at ACL 2020

Another brilliant post by Michael Galkin on usage of knowledge graphs in NLP at ACL 2020.

"Knowledge graphs demonstrate better capabilities to reveal higher-order interdependencies in otherwise unstructured data."

Content:
1. Question Answering over Structured Data
2. KG Embeddings: Hyperbolic and Hyper-relational
3. Data-to-text NLG: Prepare your Transformer
4. Conversational AI: Improving Goal-Oriented Bots
5. Information Extraction: OpenIE and Link Prediction

​​Ultimate post on where to start learning DS

Most common request we received through the years was to share insights and advices on how to start career in data science and to recommend decent cources. Apparently, using hashtag #wheretostart wasn't enough so we were sharing some general advices.

So we assembled a through guide on how to start learning machine learning and created another #ultimatepost (in a form of a github repo, so it will be keep updated and anyone can submit worthy piece of advice to it).

We welcome you to share your stories and advices on how to start rolling into data science, as well as to spread the link to the repo to those your friends who might benefit from it.

Link: Ultimate post

#entrylevel #beginner #junior #MOOC #learndatascience #courses #mlcourse #opensource

​​GPT-3 application for website form generation

Turns out #GPT3 model is capable of generating #JSX code (which is HTML layout for #React ) given the description of the required blocks to generate.

Author reports that there are exceptions, given current output limit of the model of 512 tokens.

Why this is important: one might suppose that in the future programmers will just write specifications and tests for the AI to generate the code. Given the speed of progress that won’t be surprising at all.

And probably the more sophisticated models will be capable of using hard output limit to produce a code for the output generation but that obviously is still an area for active research.

More realistic evaluation is that the upcoming code generation tools is that it will just allow more people to build products, following #nocode movement.

Twitter thread: https://twitter.com/sharifshameem/status/1282676454690451457

#codegeneration #NLU

​​Voila turns Jupyter notebooks into standalone web applications.

Unlike the usual HTML converted notebooks, each user connecting to the Voila tornado application gets a dedicated Jupyter kernel which can execute the callbacks to changes in Jupyter interactive widgets.

- By default, Voila disallows execute requests from the front-end, preventing execution of arbitrary code.
- By default, Voila runs with the strip_source option, which strips out the input cells from the rendered notebook.

https://github.com/voila-dashboards/voila

#python

Sharif Shameem improved the original app, which is now capable of generating real applications, as he demostrates with a simple ToDo app.

#GPT3 #codegeneration

The Reformer – Pushing the limits of language modeling
Patrick von Platen @ huggingface

The Reformer model was introduced by Kitaev, Kaiser et al. `20 – it is one of the most memory-efficient transformer models for long sequence modeling as of today.

The goal of this blog post is to give an in-depth understanding of each of the next four Reformer features:
[0] reformer self-attention layer – how to efficiently implement self-attention without being restricted to a local context?
[1] chunked feed forward layers – how to get a better time-memory trade-off for large feed forward layers?
[2] reversible residual layers – how to drastically reduce memory consumption in training by a smart residual architecture?
[3] axial positional encodings – how to make positional encodings usable for extremely large input sequences?

This long blog post can better allow you to understand how the model works to correctly set configurations


blog post: https://huggingface.co/blog/reformer

#nlp #reformer #huggingface #transformers

​​Do Adversarially Robust ImageNet Models Transfer Better?

TLDR - Yes.

Authors decide to check will adversarial trained network performed better on transfer learning tasks despite on worst accuracy on the trained dataset (ImageNet of course). And it is true.

They tested this idea on a frozen pre-trained feature extractor and trained only linear classifier that outperformed classic counterpart. And they tested on a full unfrozen fine-tuned network, that outperformed too on transfer learning tasks.

On pre-train task they use the adversarial robustness prior, that refers to a model’s invariance to small (often imperceptible) perturbations of its inputs.

They show also that such an approach gives better future representation properties of the networks.

They did many experiments (14 pages of graphics) and an ablation study.


paper: https://arxiv.org/abs/2007.08489
code: https://github.com/Microsoft/robust-models-transfer

#transfer_learning #SOTA #adversarial

​​how gpt3 works. a visual thread

short thread with cool animations how gpt-3 works by jay alammar

collected twitter thread: https://threader.app/thread/1285498971960598529


#nlp #transformers #gpt3 #jayalammar

#GPT3 attracted lots of attention. Let’s try new format of discussing the matter in the comments, provided by peerboard.

For accessing the comments, just click the link below ⬇️⬇️⬇️, authorize with the telegram and follow the discussion.

(Rich Sutton, author of http://www.incompleteideas.net/IncIdeas/BitterLesson.html is on the right)

Applying GPT-3 to generate neural network code

Matt Shumer used GPT-3 to generate code for a machine learning model, just by describing the dataset and required output.

#GPT3 #inception #codegeneration #NLU #NLP

​​Astrologers proclaimed the week of #codegeneration. Number of articles about the subject doubled.

Deep learning to translate between programming languages

#FacebookAI released TransCoder, an entirely self-supervised neural transcompiler system that is claimed to make code migration easier and more efficient.

ArXiV: https://arxiv.org/pdf/2006.03511.pdf
Github: https://github.com/facebookresearch/TransCoder/

#NLU #codegeneration #NLP

pytorch v1.6

[0] native mixed-precision support from nvidia (~2x perf improvement)
[1] distributed perf improvements
[2] new profiling tool for memory consumption
[3] microsoft commits to developing
[4] maintaining windows pytorch
…

github: https://github.com/pytorch/pytorch/releases/tag/v1.6.0

​​Funnel Activation for Visual Recognition

Authors offer a new activation function for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial condition.

Extensive experiments on COCO, ImageNet and CityScape show significant improvement and robustness.


Paper: https://arxiv.org/abs/2007.11824
Code: https://github.com/megvii-model/FunnelAct

#deeplearning #activationfunction #computervision #pytorch