​​A Visual Guide to Using BERT for the First Time

A new blog post and notebook by Jay Alammar to get you started with using a pre-trained BERT model for the first time. It uses huggingface libs for sentence embedding and scikitLearn for classification

blog: https://jalammar.github.io/a-visual-guide-to-using-bert-for-the-first-time

#nlp #bert

​​DeepFovea: Using deep learning for foveated reconstruction in AR/VR

DeepFovea is a network for a foveated rendering that allows reconstructing a plausible periphery with a small amount of pixels.
The reconstruction is done by finding the closest matching video to this sparse input stream of pixels on the learned manifold of natural videos.

The generator model is a U-Net with recurrent decoder blocks.
Use multiple losses to make the reconstruction plausible: adversarial loss, LPIPS loss to improve the reconstruction of the spatial details, optical flow loss to reduce the peripheral flicker.

BUT training code and weights coming soon.

blog: https://ai.facebook.com/blog/deepfovea-using-deep-learning-for-foveated-reconstruction-in-ar-vr/
code: https://github.com/facebookresearch/DeepFovea

#dl #gan

​​Altair version 3.3 released! http://altair-viz.github.io

Enhancements:
* Add inheritance structure to low-level schema classes
* Add html renderer which works across frontends
* Support Python 3.8
* Add :G shorthand for geojson type
* Add data generator interface: alt.sequence, alt.graticule, alt.sphere()
* Support geographic data sources via __geo_interface__

ODS breakfast in Paris! 🇫🇷 See you this Saturday at 10:30 at Malongo Café, 50 Rue Saint-André des Arts. We are expecting from 7 to 14 people

All the vector algebra you need for understanding neural networks

Article contains great explanations and description of matrix calculus you need to know and understand to really grok neural networks.

Link: https://explained.ai/matrix-calculus/index.html

#WhereToStart #entrylevel #novice #base #DL #nn

For those who thought that derivatives are of no real use.

Hello!

Gentle reminder in regards of second but not less historical Munich Data Science #meetup on Dec 5th jointly with BMW Welt. 160 RSVPed already, don’t miss opportunity
Evgenii +4916091541827

https://www.meetup.com/Munich-Data-Science/events/266659553

​​MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension

This method involves two sequential stages:
* coarse-tuning stage using out-of-domain datasets
* multitask learning stage using a larger in-domain dataset to help model generalize better with limited data.

Also, they propose a novel multi-step attention network (MAN) as the top-level classifier for the above task.

MMM demonstrate significantly advances the SOTA on four representative
Dialogue Multiple-Choice QA datasets

paper: https://arxiv.org/abs/1910.00458

#nlp #dialog #qa

What GPT-2 thinks of the future

Link: https://worldin.economist.com/article/17521/edition2020artificial-intelligence-predicts-future

#NLU #NLP #NLG #GPT2

Free eBook from Stanford: Introduction to Applied Linear Algebra – Vectors, Matrices, and Least Squares

Base material you need to understand how neural networks and other #ML algorithms work.

Link: https://web.stanford.edu/~boyd/vmls/

#Stanford #MOOC #WhereToStart #free #ebook #algebra #linalg #NN

​​mellotron by #NVIDIA

It's a multispeaker #voice synthesis model based on #Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data.

By explicitly conditioning on rhythm and continuous pitch contours from an audio signal or music score, Mellotron is able to generate #speech in a variety of styles ranging from reading speech to expressive speech, from slow drawls to rap and from monotonous voice to singing voice.

Unlike other methods, Mellotron trains using only read speech data without alignments between text and audio.

Site: https://nv-adlr.github.io/Mellotron
Paper: https://arxiv.org/abs/1910.11997
Git: https://github.com/NVIDIA/mellotron

New RL competition from Codeforces & collaborators

Competition involves developing a strategy / agent to win in platformer game.
Provided baseline solution contains a simple strategy — running towards nearest weapon, then to the nearest enemy, constantly shooting.

Link: competition site.

Great community event by OpenDataScience in Dubai 🏝🏙

The first Data Fest in Dubai.

Check the agenda and don't miss the event!
- Top talks from renowned experts in their fields
- Lots of new insights, skills and know-how
- Best networking with the professional community

Location: Hult International Business School
Link: https://fest.ai/dubai/

#event #dubai #ml #meta #dl

nbdev: use Jupyter Notebooks for everything

https://www.fast.ai//2019/12/02/nbdev/

github: https://github.com/fastai/nbdev/

This is a forward from an independent channel run by our fellow engineers.


@ai_machinelearning_big_data

​​FreeLB: Enhanced Adversarial Training for Language Understanding

The authors propose a novel adversarial training algorithm – FreeLB, that promotes higher robustness and invariance in the embedding space, by adding adversarial perturbations to word embeddings and minimizing the resultant adversarial risk inside different regions around input samples, applied to Transformer-based models for NLU & commonsense reasoning tasks.

Experiments on the GLUE benchmark show that when applied only to the finetuning stage, it is able to improve the overall test scores:
* of BERT-based model from 78.3 -> 79.4
* RoBERTa-large model from 88.5 -> 88.8

The proposed approach achieves SOTA single-model test accuracies of 85.44% and 67.75% on ARC-Easy and ARC-Challenge.

paper: https://arxiv.org/abs/1909.11764

#nlp #nlu #bert #adversarial #ICLR

With new TensorBoard.dev you can share your DL/ML experiments result at tensorBoard

Link: https://blog.tensorflow.org/2019/12/introducing-tensorboarddev-new-way-to.html

#DL #ML #tensorflow #tf

How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?
Chen et al., 2019 UCLA
arxiv.org/abs/1911.12360

The theory of deep learning is a new and fast-developing field. Recent studies suggest that huge over-parametrization of neural networks is not a bug, but a feature that allows deep NNs both to generalize and to be optimizable using simple (first-order gradient) optimization.
Chen et al. make another step into solving mysteries of deep learning, and their main results are:
1. Sharp optimization and generalization guarantees for deep ReLU networks
1. Better asymptotics that allows applying the theory to smaller networks (polylogarithmic instead of polynomial hidden size)
As authors say, "Our results push the study of over-parameterized deep neural networks towards more practical settings."

For a deep dive to a theory of deep learning, I suggest
iPavlov: github.com/deepmipt/tdl (Russian and English)
Stanford: stats385.github.io (English)

Artur Kuzin tells about his participation in Kaggle Open Images 2019 in English. He got a gold medal in each of the three competitions.

In this video you will find out:
🔹Description of the dataset and its markup procedures, as well as a description of the metric and its features
🔹Architecture overview of the best models
🔹Overview of tricks and hacks from the top3 of each competition
🔹Approach for quick model training

https://youtu.be/NGnOY-AzDBg

🇳🇱We received a request to setup weekly data breakfasts at Eindhoven (Holland).

Please pm @malev if you are resident or live nearby and up for joining weekly breakfasts.