Machinelearning – Telegram
383K subscribers
4.44K photos
853 videos
17 files
4.88K links
Погружаемся в машинное обучение и Data Science

Показываем как запускать любые LLm на пальцах.

По всем вопросам - @haarrp

@itchannels_telegram -🔥best channels

Реестр РКН: clck.ru/3Fmqri
Download Telegram
💻 DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation

DaisyRec-v2.0 is a Python toolkit developed for benchmarking top-N recommendation task.

Github: https://github.com/recsys-benchmark/daisyrec-v2.0

Command Generator : http://daisyrecguicommandgenerator.pythonanywhere.com/

Paper: https://arxiv.org/abs/2206.10848v1

Tutorial: https://github.com/recsys-benchmark/DaisyRec-v2.0/blob/main/DaisyRec-v2.0-Tutorial.ipynb
👍11👎4
🔊 SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning

We introduce SoundSpaces 2.0, a platform for on-the-fly geometry-based audio rendering for 3D environments.

Github: https://github.com/facebookresearch/sound-spaces

Paper: https://arxiv.org/abs/2206.08312v1

Dataset: https://paperswithcode.com/dataset/librispeech

@ai_machinelearning_big_data
👍15🔥4
Frequency Dynamic Convolution-Recurrent Neural Network (FDY-CRNN) for Sound Event Detection

Frequency Dynamic Convolution applied kernel that adapts to each freqeuncy bin of input, in order to remove tranlation equivariance of 2D convolution along the frequency axis.

Github: https://github.com/frednam93/FDY-SED

Paper: https://arxiv.org/abs/2206.11645v1

Dataset: https://paperswithcode.com/dataset/desed

@ai_machinelearning_big_data
👍15👎61
♦️ Color engineering for special images

How to improve color encoding of unnatural images.

Article
Dataset

@ai_machinelearning_big_data
👍11
🌅 Retrosynthetic Planning with Retro*

graph-based search policy that eliminates the redundant explorations of any intermediate molecules.

Github: https://github.com/binghong-ml/retro_star

Paper: https://arxiv.org/abs/2206.11477v1

Dataset: https://www.dropbox.com/s/ar9cupb18hv96gj/retro_data.zip?dl=0
👍10👎2🔥2
🦾 Bi-DexHands: Bimanual Dexterous Manipulation via Reinforcement Learning

Bi-DexHands provides a collection of bimanual dexterous manipulations tasks and reinforcement learning algorithms.

Github: https://github.com/pku-marl/dexteroushands

Isaac Gym: https://developer.nvidia.com/isaac-gym

Paper: https://arxiv.org/abs/2206.08686

@ai_machinelearning_big_data
👍14🔥2
📓 MindWare: Efficient Open-source AutoML System.

MindWare is an efficient open-source system to help users to automate the process of: 1) data pre-processing, 2) feature engineering, 3) algorithm selection, 4) architecture design, 5) hyper-parameter tuning, and 6) model ensembling.

Github: https://github.com/PKU-DAIR/mindware

Docs: https://mindware.readthedocs.io/en/latest/

Paper: https://arxiv.org/abs/2206.09423v1

@ai_machinelearning_big_data
👍15
💬 Yandex: An Open-source Yet another Language Model 100B

YaLM 100B is trained for 2 terabyte of text: dataset the Pile and web-pages, including not only Wikipedia, news articles, and books, but also Github and arxiv.org. Yandex has applied the generative neural networks YaLM in the recent Y1 search update. Now they are already helping to give answers to searches in Yandex and Alice.

Github: https://github.com/yandex/YaLM-100B

@ai_machinelearning_big_data
🔥24👍4👎4😁1
🏮 tntorch - Tensor Network Learning with PyTorch

PyTorch-powered modeling and learning library using tensor networks. Installation: pip install tntorch

Github: https://github.com/rballester/tntorch

Docs site: http://tntorch.readthedocs.io/

Paper: https://arxiv.org/abs/2206.11128v1

@ai_machinelearning_big_data
👍17
👍6
🦜 Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech

IMS Toucan is a toolkit for teaching, training and using state-of-the-art Speech Synthesis models.

Github: https://github.com/rballester/tntorch

Pre-Generated Audios: https://multilingualtoucan.github.io/

Cloning prosody across speakers: https://toucanprosodycloningdemo.github.io/

Paper: https://arxiv.org/abs/2206.12229v1

@ai_machinelearning_big_data
👍10
🗾 Insubstantial Object Detection

Dataset comprised of 600 videos (141,017 frames) covering various distances, sizes, visibility, and scenes captured by different spectral ranges.

Github: https://github.com/calayzhou/iod-video

Project: https://calayzhou.github.io/

Paper: https://arxiv.org/abs/2206.11459v1

Dataset: https://paperswithcode.com/dataset/coco

@ai_machinelearning_big_data
👍15🔥1
👍7👎5
👍33🔥5😱1
👍12👎6
🎯 A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges

Github: https://github.com/shiqiyu/opengait

Paper: https://arxiv.org/abs/2206.13732v1

Dataset: https://paperswithcode.com/dataset/usf

@ai_machinelearning_big_data
👍14