​​Politicians phone distraction tracking as an art project

Enthusiast used livestream of flemish goverment sessions to track those politicians who distracted on the phones during their worktime.

Project website: https://driesdepoorter.be/theflemishscrollers/
Twitter: https://twitter.com/FlemishScroller

#keras #neuroart #politics #ml4sg

Mava: a scalable, research framework for multi-agent reinforcement learning

The framework integrates with popular MARL environments such as PettingZoo, SMAC, RoboCup, OpenSpiel, Flatland , as well as a few custom environments.

Mava includes distributed implementations of multi-agent versions of ddpg, d4pg, dqn, ppo, as well as DIAL, VDN and QMIX.

ArXiV: https://arxiv.org/pdf/2107.01460.pdf
GitHub: https://github.com/instadeepai/Mava

#MARL #RL #dl

Natural Language Processing News

by Sebastian Ruder:

- Github Copilot: interesting upcoming technology that can leave you without job;
- The Perceiver: new architecture motivated by Transformer that can deal with very high-dimensional inputs;
- NL augementer: collaborative work that aims to collect all accepted transformations to NL; you still can participate and be a co-author of the paper!

and more here.

​​YOLOX: Exceeding YOLO Series in 2021


This paper presents a new high-performance variation of YOLO - YOLOX. Now it has an anchor-free detector, a decoupled head, and uses the leading label assignment strategy SimOTA.

Thanks to these changes, it reaches state-of-the-art results across a large scale range of models. For example, YOLOX-Nano gets 25.3% AP on COCO (+1.8% to NanoDet), YOLOX-L achieves 50.0% AP on COCO (+1.8 to YOLOv5-L).

For YOLOv3, one of the most widely used detectors in industry, they boost it to 47.3% AP on COCO, outperforming the current best practice by 3.0% AP.

The authors won the 1st Place on Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021) using a single YOLOX-L model.

They also provide deploy versions with ONNX, TensorRT, NCNN, and Openvino supported.

Paper: https://arxiv.org/abs/2107.08430

Code: https://github.com/Megvii-BaseDetection/YOLOX

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-yolox

#deeplearning #cv #objectdetection #endtoend #anchorfree

​​Orbit — An Open Source Package for Time Series Inference and Forecasting

Object-ORiented BayesIan Time Series is a new project for #timeseries forecasting by #Uber team. Has #scikit-learn compatible interface and claimed to have results comparable to #prophet .

Post: https://eng.uber.com/orbit/
Docs: https://uber.github.io/orbit/about.html
GitHub: https://github.com/uber/orbit/

New TTS Models for Minority Languages of the CIS / Russia

In collaboration with the community, we created totally unique models for the languages of the peoples of Russia / the CIS:

- Bashkir (aigul_v2)
- Kalmyk (erdni_v2)
- Tatar (dilyara_v2)
- Uzbek (dilnavoz_v2)

We also tried to create the Ukrainian voice, but the data we had (sourced from audiobooks) was not very good (all other voices were created from recordings).

Some models sound almost perfect, some a bit worse. Typically this boils down to how speakers can provide steady consistent recordings.

We used anywhere from 1 hour to 6 hours of recordings to create each voice.

These models obviously do not include automated stress and have the same major caveats as other v2 models (i.e. best used with batch size 1 on 2-4 CPU threads).

Link

- https://github.com/snakers4/silero-models#text-to-speech

​​Baidu announced opening 10k sq m park with 200 operating autonomous vehicles in China.

Source: https://twitter.com/Baidu_Inc/status/1420776376861405185

#Baidu #selfdriving

​​Tonight at 9 p.m. Moscow Time, Russia’s Krasnaya Polyana resort will host the AI & Chess meetup, bringing together data scientists and professional chess players

Location: Galaxy Mall in Krasnaya Polyana, Sochi + livestream

Program:
9-9:05 p.m.
Introductory speech.

9:05-9:25 p.m. (Rus)
Mark Glukhovsky, Executive Director of the Russian Chess Federation: “Chess and Computer Technology: What AI Is and How It Is Changing the Chess World.”

9:25-9:40 p.m. (Rus)
Conversation with Sergei Shipov, a Russian professional chess player, grandmaster, chess coach and commentator: “The Role of the Computer in Professional Chess Player Training.”

9:40-9:55 p.m. (Rus)
Aleksandr Shimanov, a Russian professional chess player, grandmaster and commentator, reviews the most incredible game from the AlphaZero vs. Stockfish match, which pitted the most powerful chess engines against each other.

9:55-10:25 p.m. (Eng)
Ulrich Paquet and Nenad Tomašev, DeepMind researchers and authors of papers on AlphaZero in collaboration with Vladimir Kramnik: “Inner Workings of Chess Algorithms Based on AI and Neural Networks: AlphaZero and Beyond.”

10:25-10:45 p.m. (Eng)
Discussion:
— Effects of technology, AI engines and applications on a chess player’s training, style and mindset.
— Challenges that arise in the use of chess engines.
— Impact of chess on life and vice versa, and how the situation has evolved with the advances in chess technology.
— Future prospects of the chess-AI symbiosis in education, entertainment and self-development.

Discussion participants:
Ulrich Paquet and Nenad Tomašev, researchers, DeepMind;
Sergey Rykovanov (professor) and Yuri Shkandybin (systems architect), Skoltech’s supercomputing group;
Aleksandr Shimanov, Russian chess player, grandmaster.

Links:
Sign up: https://surl.li/abbvc
Livestream: https://youtu.be/BDWELYal47c

🗣 Pretrained Language Model

AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models

Github: https://github.com/huawei-noah/Pretrained-Language-Model

Paper: https://arxiv.org/abs/2107.13686v1

AutoTinyBERT: https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/AutoTinyBERT

@ai_machinelearning_big_data

🎓Online Berkeley Deep Learning Lectures 2021

University of Berkeley released its fresh course lectures online for everyone to watch. Welcome Berkeley CS182/282 Deep Learnings - 2021!

YouTube: https://www.youtube.com/playlist?list=PLuv1FSpHurUevSXe_k0S7Onh6ruL-_NNh

#MOOC #wheretostart #Berkeley #dl

Tokyo Olympics Alternative medals table

Article on how teams performed with the respect to behavior expected by regression model.

Link: https://ig.ft.com/tokyo-olympics-alternative-medal-table/

​​Virtual fitting room launched by our friends

#in3D launched a 3D virtual fitting room with Replicant Fashion house. 30+ designers, 60+ looks.

Great example of the AI-driven product!

Desktop: https://www.replicant.fashion/digitaltwin
iPhone: https://apps.apple.com/us/app/in3d-3d-body-scanning/id1467153183

#aiproduct #fitting #metaverse

​​Domain-Aware Universal Style Transfer

Style transfer aims to reproduce content images with the styles from reference images. Modern style transfer methods can successfully apply arbitrary styles to images in either an artistic or a photo-realistic way. However, due to their structural limitations, they can do it only within a specific domain: the degrees of content preservation and stylization depends on a predefined target domain. As a result, both photo-realistic and artistic models have difficulty in performing the desired style transfer for the other domain.

The authors propose Domain-aware Style Transfer Networks (DSTN) that transfer not only the style but also the property of domain (i.e., domainness) from a given reference image. Furthermore, they design a novel domainess indicator (based on the texture and structural features) and introduce a unified framework with domain-aware skip connection to adaptively transfer the stroke and palette to the input contents guided by the domainness indicator.

Extensive experiments validate that their model produces better qualitative results and outperforms previous methods in terms of proxy metrics on both artistic and photo-realistic stylizations.

Paper: https://arxiv.org/abs/2108.04441

Code: https://github.com/Kibeom-Hong/Domain-Aware-Style-Transfer

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-dstn

#deeplearning #cv #styletransfer

14 seconds of April #Nvidia 's CEO speech was generated in silico

Why this important: demand for usage of 3080 and newer GPU models might also get pumped by CGI artists and researchers working in VR / AR tech.

And this raises the bar for #speechsinthesis / #speechgeneration and definately for the rendering of photorealistic picture.

YouTube making of video: https://www.youtube.com/watch?v=1qhqZ9ECm70&t=1430s
Vice article on the subject: https://www.vice.com/en/article/88nbpa/nvidia-reveals-its-ceo-was-computer-generated-in-keynote-speech

​​Program Synthesis with Large Language Models

Paper compares models used for program synthesis in general purpose programming languages against two new benchmarks, MBPP (The Mostly Basic Programming Problems) and MathQA-Python, in both the few-shot and fine-tuning regimes.

MBPP contains 974 programming tasks, designed to be solvable by entry-level programmers. MathQA benchmark, contains 23914 problems that evaluate the ability of the models to synthesize code from more complex text.

Largest fine-tuned model achieves 83.8 percent accuracy on the latter benchmark.

Why this is interesting: better models for code / problem understanding means improved search for the coding tasks and the improvement of the coding-assistant projects like #TabNine or #Copilot

ArXiV: https://arxiv.org/abs/2108.07732

#DL #NLU #codewritingcode #benchmark

Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity

#Baidu research proposed a structure-aware interactive graph neural network ( #SIGN ) to better learn representations of protein-ligand complexes, since drug discovery relies on the successful prediction of protein-ligand binding affinity.

Link: https://dl.acm.org/doi/10.1145/3447548.3467311

#biolearning #deeplearning

​​⚡️Breeaking news!

Big project, first public release! From the creator of FastAPI and Typer: SQLModel.

SQLModel is a library for interacting with SQL databases from Python code, with Python objects. It is designed to be intuitive, easy to use, highly compatible, and robust.

SQLModel is based on Python type annotations, and powered by Pydantic and SQLAlchemy.
SQLModel is, in fact, a thin layer on top of Pydantic and SQLAlchemy, carefully designed to be compatible with both.

The key features are:
- Intuitive to write: Great editor support. Completion everywhere. Less time debugging. Designed to be easy to use and learn. Less time reading docs.
- Easy to use: It has sensible defaults and does a lot of work underneath to simplify the code you write.
- Compatible: It is designed to be compatible with FastAPI, Pydantic, and SQLAlchemy.
- Extensible: You have all the power of SQLAlchemy and Pydantic underneath.
- Short: Minimize code duplication. A single type annotation does a lot of work. No need to duplicate models in SQLAlchemy and Pydantic.

https://github.com/tiangolo/sqlmodel

New German V4 Model and English V5 Models

New and improved models in Silero-models! Community edition versions available here: https://github.com/snakers4/silero-models

Huge performance improvements for two new models:

- English V5 (quality)
- German V3 (quality)

The models currently are available in the following flavors:

- English V5 jit (small), onnx (small), jit_q (small, quantized), jit_xlarge, onnx_xlarge
- German V3 jit_large, onnx_large

The xsmall model family for English in on the way.

The quality growth visualization: