Register for the International Data Analysis Olympiad (IDAO-2021)! The registration continues until March 12.

This year, HSE Faculty of Computer Science and Yandex are holding the Olympiad for the fourth time. This year's Platinum Partner is ‘Otkritie’ Bank. The Olympiad is organised by leading data analysts for their future colleagues, early career analysts and scientists.

The online tour will focus on the search for dark matter - one of the few remaining mysteries of fundamental physics. Dark matter cannot be seen because it does not interact with light and interacts very weakly with ordinary matter. The task of IDAO participants is to build a model that recognises some known observation processes, so that they can be excluded from the search for dark matter.

Details and registration https://idao.world

Anycost GAN

Anycost GANs for Interactive Image Synthesis and Editing

https://hanlab.mit.edu/projects/anycost-gan/

Github: https://github.com/mit-han-lab/anycost-gan

Paper: https://arxiv.org/abs/2103.03243

@ai_machinelearning_big_data

RTAB-Map

Real-Time Appearance-Based Mapping

http://introlab.github.io/rtabmap/

Github: https://github.com/introlab/rtabmap

Paper: https://arxiv.org/abs/2103.03827v1

@ai_machinelearning_big_data

Precise Multi-Neuron Abstractions for Neural Network Certification

Github : https://github.com/eth-sri/eran

Paper: https://arxiv.org/abs/2103.03638v1

@ai_machinelearning_big_data

👔 Virtual Try-on via Distilling Appearance Flows, CVPR 2021

Github: https://github.com/geyuying/PF-AFN

Paper: https://arxiv.org/abs/2103.04559

@ai_machinelearning_big_data

Train and serve a TensorFlow model with TensorFlow Serving

https://www.tensorflow.org/tfx/tutorials/serving/rest_simple

Code: https://github.com/tensorflow/tfx/blob/master/docs/tutorials/serving/rest_simple.ipynb

Dataset: https://github.com/zalandoresearch/fashion-mnist

@ai_machinelearning_big_data

Involution: Inverting the Inherence of Convolution for Visual Recognition

Github: https://github.com/d-li14/involution

Paper: https://arxiv.org/abs/2103.06255

OpenMMLab: https://openmmlab.com/

@ai_machinelearning_big_data

Strawberry Fields is a full-stack Python library for designing, simulating, and optimizing continuous-variable quantum optical circuits.

Github: https://github.com/XanaduAI/strawberryfields

Paper: https://arxiv.org/pdf/2103.05530v1.pdf

@ai_machinelearning_big_data

MagFace: A Universal Representation for Face Recognition and Quality Assessment

Github: https://github.com/IrvingMeng/MagFace

Paper: https://arxiv.org/abs/2103.06627

Code example: https://github.com/IrvingMeng/MagFace/blob/main/inference/examples.ipynb

@ai_machinelearning_big_data

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

Github: https://github.com/hkchengrex/MiVOS

Paper: https://arxiv.org/pdf/2103.07941v1.pdf

@ai_machinelearning_big_data

Open Avatarify Photorealistic avatars for video-conferencing apps. Democratized.

Github: https://github.com/alievk/avatarify-python

Demo: https://www.youtube.com/watch?v=Q7LFDT-FRzs&feature=youtu.be&ab_channel=AliAliev

@ai_machinelearning_big_data

Probabilistic two-stage detection

Two-stage object detectors that use class-agnostic one-stage detectors as the proposal network.

Github: https://github.com/xingyizhou/CenterNet2

Paper: https://arxiv.org/abs/2103.07461v1


@ai_machinelearning_big_data

🔷 PyTorch Geometric Temporal is a temporal (dynamic) extension library for PyTorch Geometric.

Github: https://github.com/benedekrozemberczki/pytorch_geometric_temporal

Paper: https://dl.acm.org/doi/10.1145/3308560.3316581

Dataset: https://pytorch-geometric-temporal.readthedocs.io/en/latest/notes/introduction.html#discrete-time-datasets

@ai_machinelearning_big_data

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks, ICLR 2021 (Spotlight)

Gitub: https://github.com/zsyzzsoft/co-mod-gan

Paper: https://openreview.net/pdf?id=sSjqmfsk95O

Demo: http://comodgan.ml/

@ai_machinelearning_big_data

Contrastive Learning of Musical Representations

Github: https://github.com/spijkervet/CLMR

Paper: https://arxiv.org/abs/2103.09410

@ai_machinelearning_big_data

🔬 The Best ML Frameworks & Extensions for Scikit-learn

https://neptune.ai/blog/the-best-ml-framework-extensions-for-scikit-learn

@ai_machinelearning_big_data

The last article in uplift modeling tutorials by MTS data scientists: “Metrics in uplift modeling”📈

Uplift models are used to promote products and create advertising segments 🤑

📗 Habr: https://habr.com/ru/company/ru_mts/blog/538934/
💻 Code: https://nbviewer.jupyter.org/github/maks-sh/scikit-uplift/blob/master/notebooks/uplift_metrics_tutorial.ipynb

The GENRE (Generarive ENtity REtrieval) system as presented in Autoregressive Entity Retrieval implemented in pytorch.

Github: https://github.com/facebookresearch/GENRE

Paper: https://arxiv.org/abs/2103.12528v1

Dataset: https://github.com/facebookresearch/GENRE/blob/main/noscripts/download_all_datasets.sh

@ai_machinelearning_big_data

Каждый день мы загружаем и передаем все больше контента. Нагрузка на базовые станции операторов растет, но вместе с ней растет и качество связи. Как это получается? И какую роль в этом процессе играет big data?

Ответы найдете в видео «Как нейросети помогают оставаться на связи», где Тимур и Вика, датасайентисты из МегаФона, рассказывают, почему модернизация базовых станций – это задача из области data science, как работает модель, на основании рекомендаций которой принимаются решения о необходимости «прокачки» той или иной вышки, и остается ли в этом процессе место для человека.

Спойлер: место для человека остается. Например, в МегаФоне в команду по работе с большими данными ищут Team Lead, Senior data scientist, инженера SQL и других специалистов.

Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization

Github: https://github.com/czczup/URST

Paper: https://arxiv.org/abs/2103.11784

Dataset: https://cocodataset.org/#download

@ai_machinelearning_big_data