Тут у Яндекса интересная новость. Компания запускает соревнование для исследователей в области машинного обучения в рамках крупнейшей конференции MLщиков в мире - NeurIPS 2021. Вместе с учеными Оксфорда и Кембриджа предлагают участникам посоревноваться в разработке алгоритмов и их обучении для погоды, машинного перевода текстов и предсказания поведения участников автомобильного движения. Основной задачей будет проверить эффективность этих алгоритмов при сдвиге данных.
Для соревнования Яндекс открыл доступ к собственному датасету, который считается самым большим в мире по беспилотным автомобилям. Еще поделятся реальными данными Я.Погоды и Я.Переводчика. Это данные из сервисов, которые много лет работают в реальном мире, используются в различных сценариях, и уже проходили испытание сдвигом данных.
Полученные решения можно будет применять в разных отраслях, которые сталкиваются со сдвигом данных. Крутая инициатива!
https://research.yandex.com/shifts
Для соревнования Яндекс открыл доступ к собственному датасету, который считается самым большим в мире по беспилотным автомобилям. Еще поделятся реальными данными Я.Погоды и Я.Переводчика. Это данные из сервисов, которые много лет работают в реальном мире, используются в различных сценариях, и уже проходили испытание сдвигом данных.
Полученные решения можно будет применять в разных отраслях, которые сталкиваются со сдвигом данных. Крутая инициатива!
https://research.yandex.com/shifts
Shifts Challenge: Robustness and Uncertainty under Real-World Distributional Shift
We invite researchers and machine learning practitioners from all over the world to participate in our NeurIPS 2021 Shifts Challenge on robustness and uncertainty under real-world distributional shift.
https://news.1rj.ru/str/Golang_google - golang channel
https://news.1rj.ru/str/javanoscriptv - javanoscript tutorials
https://news.1rj.ru/str/memes_prog - it memes
https://news.1rj.ru/str/pro_python_code - python ru
https://news.1rj.ru/str/htmlcssjavas - web development
https://news.1rj.ru/str/csharp_ci - c sharp
https://news.1rj.ru/str/linuxkalii - kali linux
https://news.1rj.ru/str/javanoscriptv - javanoscript tutorials
https://news.1rj.ru/str/memes_prog - it memes
https://news.1rj.ru/str/pro_python_code - python ru
https://news.1rj.ru/str/htmlcssjavas - web development
https://news.1rj.ru/str/csharp_ci - c sharp
https://news.1rj.ru/str/linuxkalii - kali linux
🔎 Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Github: https://github.com/xinntao/Real-ESRGAN
Paper: https://arxiv.org/abs/2107.10833v1
How to Train Real-ESRGAN: https://github.com/xinntao/Real-ESRGAN/blob/master/Training.md
Colab Demo: https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo
@ai_machinelearning_big_data
Github: https://github.com/xinntao/Real-ESRGAN
Paper: https://arxiv.org/abs/2107.10833v1
How to Train Real-ESRGAN: https://github.com/xinntao/Real-ESRGAN/blob/master/Training.md
Colab Demo: https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo
@ai_machinelearning_big_data
AAVAE: Augmentation-Augmented Variational Autoencoders
Github: https://github.com/gridai-labs/aavae
Paper: https://arxiv.org/abs/2107.12329v1
Dataset: https://paperswithcode.com/dataset/cifar-10
@ai_machinelearning_big_data
Github: https://github.com/gridai-labs/aavae
Paper: https://arxiv.org/abs/2107.12329v1
Dataset: https://paperswithcode.com/dataset/cifar-10
@ai_machinelearning_big_data
📂 RLQP: Accelerating Quadratic Optimization with RL
Github: https://github.com/berkeleyautomation/rlqp
Paper: https://arxiv.org/abs/2107.10833v1
@ai_machinelearning_big_data
Github: https://github.com/berkeleyautomation/rlqp
Paper: https://arxiv.org/abs/2107.10833v1
@ai_machinelearning_big_data
🖊 Introducing Triton: Open-Source GPU Programming for Neural Networks
https://openai.com/blog/triton/
Github: https://github.com/openai/triton
Documents: https://triton-lang.org/
@ai_machinelearning_big_data
https://openai.com/blog/triton/
Github: https://github.com/openai/triton
Documents: https://triton-lang.org/
@ai_machinelearning_big_data
👁 Contextual Transformer Networks for Visual Recognition.
Github: https://github.com/JDAI-CV/CoTNet
Paper: https://arxiv.org/abs/2107.12292v1
Chalange: https://eval.ai/web/challenges/challenge-page/1041/leaderboard/2695
@ai_machinelearning_big_data
Github: https://github.com/JDAI-CV/CoTNet
Paper: https://arxiv.org/abs/2107.12292v1
Chalange: https://eval.ai/web/challenges/challenge-page/1041/leaderboard/2695
@ai_machinelearning_big_data
🌠 Deepmind's Generally capable agents emerge from open-ended play
Blog : https://deepmind.com/blog/article/generally-capable-agents-emerge-from-open-ended-play
Paper: https://deepmind.com/research/publications/open-ended-learning-leads-to-generally-capable-agents
DeepMind Research: https://github.com/deepmind/deepmind-research
Video: https://www.youtube.com/watch?v=lTmL7jwFfdw&ab_channel=DeepMind
@ai_machinelearning_big_data
Blog : https://deepmind.com/blog/article/generally-capable-agents-emerge-from-open-ended-play
Paper: https://deepmind.com/research/publications/open-ended-learning-leads-to-generally-capable-agents
DeepMind Research: https://github.com/deepmind/deepmind-research
Video: https://www.youtube.com/watch?v=lTmL7jwFfdw&ab_channel=DeepMind
@ai_machinelearning_big_data
🤖 Droidlet: modular, heterogenous, multi-modal agents
Github: https://github.com/facebookresearch/droidlet
Paper: https://arxiv.org/abs/2101.10384
Article: https://news.1rj.ru/str/machinelearning_ru/279
@ai_machinelearning_big_data
Github: https://github.com/facebookresearch/droidlet
Paper: https://arxiv.org/abs/2101.10384
Article: https://news.1rj.ru/str/machinelearning_ru/279
@ai_machinelearning_big_data
🗣 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
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
📡 StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
Github: https://github.com/rinongal/StyleGAN-nada
Paper: https://arxiv.org/abs/2108.00946v1
Project: https://stylegan-nada.github.io/
Dataset: https://paperswithcode.com/dataset/lsun
@ai_machinelearning_big_data
Github: https://github.com/rinongal/StyleGAN-nada
Paper: https://arxiv.org/abs/2108.00946v1
Project: https://stylegan-nada.github.io/
Dataset: https://paperswithcode.com/dataset/lsun
@ai_machinelearning_big_data
🥑 DALL·E Mini
Generate images from a text prompt
Demo: https://huggingface.co/spaces/flax-community/dalle-mini
Github: https://github.com/borisdayma/dalle-mini
Paper: https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini--Vmlldzo4NjIxODA
@ai_machinelearning_big_data
Generate images from a text prompt
Demo: https://huggingface.co/spaces/flax-community/dalle-mini
Github: https://github.com/borisdayma/dalle-mini
Paper: https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini--Vmlldzo4NjIxODA
@ai_machinelearning_big_data
huggingface.co
DALL·E mini by craiyon.com on Hugging Face
Enter a text prompt, and the app will generate images based on your denoscription. You can download the generated images as well.
📥 Toward Spatially Unbiased Generative Models
Github: https://github.com/jychoi118/toward_spatial_unbiased
Paper: https://arxiv.org/abs/2108.01285v1
@ai_machinelearning_big_data
Github: https://github.com/jychoi118/toward_spatial_unbiased
Paper: https://arxiv.org/abs/2108.01285v1
@ai_machinelearning_big_data
GitHub
GitHub - jychoi118/toward_spatial_unbiased: Toward Spatially Unbiased Generative Models (ICCV 2021)
Toward Spatially Unbiased Generative Models (ICCV 2021) - jychoi118/toward_spatial_unbiased
▶️ Deepminds's Perceiver: General Perception with Iterative Attention
General architecture that works on many kinds of data
https://deepmind.com/blog/article/building-architectures-that-can-handle-the-worlds-data
Github: https://github.com/deepmind/deepmind-research/tree/master/perceiver
Colab: https://colab.research.google.com/github/deepmind/deepmind_research/blob/master/perceiver/colabs/masked_language_modelling.ipynb
Paper: https://arxiv.org/abs/2103.03206
@ai_machinelearning_big_data
General architecture that works on many kinds of data
https://deepmind.com/blog/article/building-architectures-that-can-handle-the-worlds-data
Github: https://github.com/deepmind/deepmind-research/tree/master/perceiver
Colab: https://colab.research.google.com/github/deepmind/deepmind_research/blob/master/perceiver/colabs/masked_language_modelling.ipynb
Paper: https://arxiv.org/abs/2103.03206
@ai_machinelearning_big_data
How to automate Hadoop administration without excruciating pain
https://habr.com/ru/company/ru_mts/blog/569762/
@ai_machinelearning_big_data
https://habr.com/ru/company/ru_mts/blog/569762/
@ai_machinelearning_big_data
📸 Physics-based Noise Modeling for Extreme Low-light Photography
Github: https://github.com/Vandermode/ELD
Paper: https://arxiv.org/abs/2108.02158v1
Dataset: https://drive.google.com/drive/folders/1CT2Ny9W9ArdSQaHNxC5hGwav9lZHoqJa?usp=sharing
@ai_machinelearning_big_data
Github: https://github.com/Vandermode/ELD
Paper: https://arxiv.org/abs/2108.02158v1
Dataset: https://drive.google.com/drive/folders/1CT2Ny9W9ArdSQaHNxC5hGwav9lZHoqJa?usp=sharing
@ai_machinelearning_big_data
👍1
👁 Improving Contrastive Learning by Visualizing Feature Transformation
Github: https://github.com/DTennant/CL-Visualizing-Feature-Transformation
Paper: https://arxiv.org/abs/2108.02982
@ai_machinelearning_big_data
Github: https://github.com/DTennant/CL-Visualizing-Feature-Transformation
Paper: https://arxiv.org/abs/2108.02982
@ai_machinelearning_big_data
📹 Internal Video Inpainting by Implicit Long-range Propagation
Github: https://github.com/Tengfei-Wang/Implicit-Internal-Video-Inpainting
Paper: https://arxiv.org/abs/2108.01912v1
4k Data: https://github.com/Tengfei-Wang/Annotated-4K-Videos
Dataset: https://paperswithcode.com/dataset/videoremoval4k
@ai_machinelearning_big_data
Github: https://github.com/Tengfei-Wang/Implicit-Internal-Video-Inpainting
Paper: https://arxiv.org/abs/2108.01912v1
4k Data: https://github.com/Tengfei-Wang/Annotated-4K-Videos
Dataset: https://paperswithcode.com/dataset/videoremoval4k
@ai_machinelearning_big_data
🔍 Contrastive Sensor Fusion
Github: https://github.com/descarteslabs/contrastive_sensor_fusion
Paper: https://arxiv.org/abs/2108.05094v1
@ai_machinelearning_big_data
Github: https://github.com/descarteslabs/contrastive_sensor_fusion
Paper: https://arxiv.org/abs/2108.05094v1
@ai_machinelearning_big_data
🎨 Paint Transformer: Feed Forward Neural Painting with Stroke Prediction
Github: https://github.com/huage001/painttransformer
Paper: https://arxiv.org/abs/2108.03798
Paddle Implementation: https://github.com/PaddlePaddle/PaddleGAN
@ai_machinelearning_big_data
Github: https://github.com/huage001/painttransformer
Paper: https://arxiv.org/abs/2108.03798
Paddle Implementation: https://github.com/PaddlePaddle/PaddleGAN
@ai_machinelearning_big_data