🔥 Awesome list of datasets in 100+ categories
44 zettabytes of data
https://www.kdnuggets.com/2021/05/awesome-list-datasets.html
@ai_machinelearning_big_data
44 zettabytes of data
https://www.kdnuggets.com/2021/05/awesome-list-datasets.html
@ai_machinelearning_big_data
🎉 24 мая в Москве наградили молодых ученых и их наставников, занимающихся научной работой в области компьютерных наук. Поздравляем лауреатов премии имени Ильи Сегаловича! 🎉
Каждый из них получит по 1 миллиону рублей, который будет можно потратить на собственные исследования. В этом году Совет премии отметил шесть исследователей из НИУ ВШЭ, МФТИ и Сколковского института науки и технологий.
⚠️ Узнайте больше о тех, кто получил премию, и как принять в ней участие: https://clck.ru/V3QDF
Каждый из них получит по 1 миллиону рублей, который будет можно потратить на собственные исследования. В этом году Совет премии отметил шесть исследователей из НИУ ВШЭ, МФТИ и Сколковского института науки и технологий.
⚠️ Узнайте больше о тех, кто получил премию, и как принять в ней участие: https://clck.ru/V3QDF
Yandex ML Prize
Премия Яндекса для учёных и преподавателей в области Machine Learning
👍1
🧠 NeuroKit2: A Python toolbox for neurophysiological signal processing
A user-friendly package providing easy access to advanced biosignal processing routines.
Github: https://github.com/neuropsychology/NeuroKit
Paper: https://link.springer.com/article/10.3758/s13428-020-01516-y
Docs: https://neurokit2.readthedocs.io/en/latest/installation.html
@ai_machinelearning_big_data
A user-friendly package providing easy access to advanced biosignal processing routines.
Github: https://github.com/neuropsychology/NeuroKit
Paper: https://link.springer.com/article/10.3758/s13428-020-01516-y
Docs: https://neurokit2.readthedocs.io/en/latest/installation.html
@ai_machinelearning_big_data
❤1
✔️ GPBoost: Combining Tree-Boosting with Gaussian Process and Mixed Effects Models
Github: https://github.com/fabsig/GPBoost
Demo code: https://htmlpreview.github.io/?https://github.com/fabsig/GPBoost/blob/master/examples/GPBoost_demo.html
Paper: https://arxiv.org/abs/2105.08966v2
@ai_machinelearning_big_data
Github: https://github.com/fabsig/GPBoost
Demo code: https://htmlpreview.github.io/?https://github.com/fabsig/GPBoost/blob/master/examples/GPBoost_demo.html
Paper: https://arxiv.org/abs/2105.08966v2
@ai_machinelearning_big_data
🗯 Unsupervised Speech Recognition
Github: https://github.com/pytorch/fairseq/tree/master/examples/wav2vec/unsupervised
Pretraned model: https://github.com/pytorch/fairseq/tree/master/examples/wav2vec
Facebook blog: https://ai.facebook.com/blog/wav2vec-unsupervised-speech-recognition-without-supervision/
Paper
@ai_machinelearning_big_data
Github: https://github.com/pytorch/fairseq/tree/master/examples/wav2vec/unsupervised
Pretraned model: https://github.com/pytorch/fairseq/tree/master/examples/wav2vec
Facebook blog: https://ai.facebook.com/blog/wav2vec-unsupervised-speech-recognition-without-supervision/
Paper
@ai_machinelearning_big_data
👍1
Yolov5-face is a real-time,high accuracy face detection
Github: https://github.com/deepcam-cn/yolov5-face
Paper: https://arxiv.org/abs/2105.12931v1
@ai_machinelearning_big_data
Github: https://github.com/deepcam-cn/yolov5-face
Paper: https://arxiv.org/abs/2105.12931v1
@ai_machinelearning_big_data
💥Grokking Artificial Intelligence Algorithms
⬇️ Download
💥Grokking Deep Reinforcement Learning
⬇️ Download
@ai_machinelearning_big_data
⬇️ Download
💥Grokking Deep Reinforcement Learning
⬇️ Download
@ai_machinelearning_big_data
🏎 Make Pandas 3 Times Faster with PyPolars
Code : https://www.kdnuggets.com/2021/05/pandas-faster-pypolars.html
Github: https://github.com/pola-rs/polars
User Guide: https://pola-rs.github.io/polars-book
@ai_machinelearning_big_data
Code : https://www.kdnuggets.com/2021/05/pandas-faster-pypolars.html
Github: https://github.com/pola-rs/polars
User Guide: https://pola-rs.github.io/polars-book
@ai_machinelearning_big_data
You Only 👀 One Sequence
Rethinking Transformer in Vision through Object Detection
Github: https://paperswithcode.com/paper/you-only-look-at-one-sequence-rethinking
Dataset: https://paperswithcode.com/dataset/imagenet
Paper: https://arxiv.org/abs/2106.00666
@ai_machinelearning_big_data
Rethinking Transformer in Vision through Object Detection
Github: https://paperswithcode.com/paper/you-only-look-at-one-sequence-rethinking
Dataset: https://paperswithcode.com/dataset/imagenet
Paper: https://arxiv.org/abs/2106.00666
@ai_machinelearning_big_data
👍1
🌏 The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation
Github: https://github.com/facebookresearch/flores
Paper: https://ai.facebook.com/research/publications/the-flores-101-evaluation-benchmark-for-low-resource-and-multilingual-machine-translation
Facebook blog: https://ai.facebook.com/blog/the-flores-101-data-set-helping-build-better-translation-systems-around-the-world/
@ai_machinelearning_big_data
Github: https://github.com/facebookresearch/flores
Paper: https://ai.facebook.com/research/publications/the-flores-101-evaluation-benchmark-for-low-resource-and-multilingual-machine-translation
Facebook blog: https://ai.facebook.com/blog/the-flores-101-data-set-helping-build-better-translation-systems-around-the-world/
@ai_machinelearning_big_data
This media is not supported in your browser
VIEW IN TELEGRAM
🤖 DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Project: https://dynamicvit.ivg-research.xyz/
Github: https://github.com/raoyongming/DynamicViT
Paper: https://arxiv.org/abs/2106.02034
@ai_machinelearning_big_data
Project: https://dynamicvit.ivg-research.xyz/
Github: https://github.com/raoyongming/DynamicViT
Paper: https://arxiv.org/abs/2106.02034
@ai_machinelearning_big_data
X5 Group проводит собственное мероприятие X5Tech Future Night о технологиях и бизнесе. Большое летнее офлайн событие объединит на одной площадке разные форматы: лекции, паблик-интервью, бизнес-дебаты, дискуссии и музыкальный оупен-эйр.
В программе есть отдельная секция, посвященная Big Data, а именно тому, как монетизировать данные и превратить их в новые продукты.
Участие бесплатное, регистрируйтесь сейчас, чтобы не пропустить. Количество мест ограничено!
В программе есть отдельная секция, посвященная Big Data, а именно тому, как монетизировать данные и превратить их в новые продукты.
Участие бесплатное, регистрируйтесь сейчас, чтобы не пропустить. Количество мест ограничено!
📈 NGBoost: Natural Gradient Boosting for Probabilistic Prediction
Github: https://github.com/stanfordmlgroup/ngboost
Slides: https://drive.google.com/file/d/183BWFAdFms81MKy6hSku8qI97OwS_JH_/view
Paper: https://arxiv.org/abs/2106.03823v1
@ai_machinelearning_big_data
Github: https://github.com/stanfordmlgroup/ngboost
Slides: https://drive.google.com/file/d/183BWFAdFms81MKy6hSku8qI97OwS_JH_/view
Paper: https://arxiv.org/abs/2106.03823v1
@ai_machinelearning_big_data
🔥2
🧠 Yet Another Language Model — нейросетевой языковой алгоритм генерации текстов, разработанный Яндексом
Paper : https://wow.link/Er21
@ai_machinelearning_big_data
Paper : https://wow.link/Er21
@ai_machinelearning_big_data
👍1👎1🔥1
👨 TFace: A trusty face recognition research platform
Github: https://github.com/Tencent/TFace
Paper: https://arxiv.org/abs/2106.05519v1
@ai_machinelearning_big_data
Github: https://github.com/Tencent/TFace
Paper: https://arxiv.org/abs/2106.05519v1
@ai_machinelearning_big_data
Microsoft's FLAML - Fast and Lightweight AutoML
Github: https://github.com/microsoft/FLAML
Code: https://github.com/microsoft/FLAML/tree/main/notebook/
Paper: https://arxiv.org/abs/2106.04815v1
@ai_machinelearning_big_data
Github: https://github.com/microsoft/FLAML
Code: https://github.com/microsoft/FLAML/tree/main/notebook/
Paper: https://arxiv.org/abs/2106.04815v1
@ai_machinelearning_big_data
✅ Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs
Github: https://github.com/seongjunyun/Graph_Transformer_Networks
Paper: https://arxiv.org/abs/2106.06218v1
Dataset: https://github.com/Jhy1993/HAN
@ai_machinelearning_big_data
Github: https://github.com/seongjunyun/Graph_Transformer_Networks
Paper: https://arxiv.org/abs/2106.06218v1
Dataset: https://github.com/Jhy1993/HAN
@ai_machinelearning_big_data
🧩 A Bayesian Analysis of Lego Prices in Python with PyMC3
https://austinrochford.com/posts/2021-06-10-lego-pymc3.html
Lego Price Analysis: https://austinrochford.com/posts/2021-06-03-vader-meditation.html
@ai_machinelearning_big_data
https://austinrochford.com/posts/2021-06-10-lego-pymc3.html
Lego Price Analysis: https://austinrochford.com/posts/2021-06-03-vader-meditation.html
@ai_machinelearning_big_data
Facebook's Reverse engineering generative models from a single deepfake image
Github: https://github.com/vishal3477/Reverse_Engineering_GMs
Paper: https://arxiv.org/abs/2106.07873
Facebook's blog: https://ai.facebook.com/blog/reverse-engineering-generative-model-from-a-single-deepfake-image/
Dataset: https://drive.google.com/drive/folders/1ZKQ3t7_Hip9DO6uwljZL4rYAn5viSRhu?usp=sharing
@ai_machinelearning_big_data
Github: https://github.com/vishal3477/Reverse_Engineering_GMs
Paper: https://arxiv.org/abs/2106.07873
Facebook's blog: https://ai.facebook.com/blog/reverse-engineering-generative-model-from-a-single-deepfake-image/
Dataset: https://drive.google.com/drive/folders/1ZKQ3t7_Hip9DO6uwljZL4rYAn5viSRhu?usp=sharing
@ai_machinelearning_big_data
⬇️ Pysentimiento: A Python toolkit for Sentiment Analysis and Social NLP tasks
Github: https://github.com/pysentimiento/pysentimiento
Paper: https://arxiv.org/abs/2106.09462
English model: https://huggingface.co/finiteautomata/bertweet-base-sentiment-analysis
@ai_machinelearning_big_data
Github: https://github.com/pysentimiento/pysentimiento
Paper: https://arxiv.org/abs/2106.09462
English model: https://huggingface.co/finiteautomata/bertweet-base-sentiment-analysis
@ai_machinelearning_big_data
👍1