¡Ya disponible! Investigación de Telegram 2025 — los principales insights del año 
Machinelearning
Ir al canal en Telegram
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
Mostrar más📈 Análisis del canal de Telegram Machinelearning
El canal Machinelearning (@ai_machinelearning_big_data) en el segmento lingüístico de Ruso es un actor destacado. Actualmente la comunidad reúne a 293 399 suscriptores, ocupando la posición 326 en la categoría Tecnologías y Aplicaciones y el puesto 1 283 en la región Rusia.
📊 Métricas de audiencia y dinámica
Desde su creación el невідомо, el proyecto ha mostrado un crecimiento acelerado, reuniendo a 293 399 suscriptores.
Según los últimos datos del 03 julio, 2026, el canal mantiene una actividad estable. En los últimos 30 días la variación de miembros fue de -6 469, y en las últimas 24 horas de -218, conservando un alto alcance.
- Estado de verificación: No verificado
- Tasa de interacción (ER): El promedio de interacción de la audiencia es 7.32%. Durante las primeras 24 horas tras publicar, el contenido suele obtener 5.77% de reacciones respecto al total de suscriptores.
- Alcance de las publicaciones: Cada publicación recibe en promedio 21 487 visualizaciones. En el primer día suele acumular 16 937 visualizaciones.
- Reacciones e interacción: La audiencia responde de forma activa: el promedio de reacciones por publicación es 169.
- Intereses temáticos: El contenido se centra en temas clave como openai, claude, api, gemini, контекст.
📝 Descripción y política de contenido
El autor describe el recurso como un espacio para expresar opiniones subjetivas:
“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”
Gracias a la alta frecuencia de actualizaciones (últimos datos recibidos el 04 julio, 2026), el canal mantiene la vigencia y un amplio alcance. La analítica demuestra que la audiencia interactúa activamente con el contenido, lo que lo convierte en un punto de referencia dentro de la categoría Tecnologías y Aplicaciones.
293 399
Suscriptores
-21824 horas
-1 5287 días
-6 46930 días
Archivo de publicaciones
293 404
From singing to musical scores: Estimating pitch with SPICE and Tensorflow Hub
Pitch is quantified by frequency, measured in Hertz (Hz), where one Hz corresponds to one cycle per second. The higher the frequency, the higher the note.
https://blog.tensorflow.org/2020/06/estimating-pitch-with-spice-and-tensorflow-hub.html
Model: https://tfhub.dev/google/spice/2
Colab code: https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/spice.ipynb
293 404
Using Multi-Scale Attention for Semantic Segmentation
https://devblogs.nvidia.com/using-multi-scale-attention-for-semantic-segmentation/
Paper: https://arxiv.org/abs/2005.10821
293 404
Rethinking the Truly Unsupervised Image-to-Image Translation - Official PyTorch Implementation
Here proposed the truly unsupervised image-to-image translation method (TUNIT) that simultaneously learns to separate image domains via an information-theoretic approach and generate corresponding images using the estimated domain labels.
Github: https://github.com/clovaai/tunit
Paper: https://arxiv.org/abs/2006.06500v1
293 404
Synthesizing High-Resolution Images with StyleGAN2
https://www.youtube.com/watch?v=9QuDh3W3lOY&feature=emb_logo
Article: https://news.developer.nvidia.com/synthesizing-high-resolution-images-with-stylegan2/
293 404
Хайп вокруг Big Data уже прошёл, но идеальное хранилище под большие данные — всегда актуальная тема: чтобы легко масштабировалось под любой объем и предоставляло расширенные возможности по обработке данных.
Современные базы бывают именно такими. Мы расскажем, почему DWH лучше строить в облаке и какие есть Best Practice для архитектуры.
👉 Регистрируйтесь на наш вебинар про управляемую СУБД на основе Greenplum, разработанную специально для решения аналитических задач — от BI до AI.
Встретимся в четверг 18 июня, онлайн. Начало в 17:00 по Москве, регистрация обязательна: https://events.webinar.ru/mcs/arenadatadb
293 404
Now Open STT Featured On Azure Datasets
https://azure.microsoft.com/en-us/services/open-datasets/catalog/open-speech-to-text/
293 404
VirTex: Learning Visual Representations from Textual Annotations
VirTex is a pretraining approach which uses semantically dense captions to learn visual representations.VirTex matches or outperforms models which use ImageNet for pretraining -- both supervised or unsupervised -- despite using up to 10x fewer images.
https://kdexd.github.io/virtex/
Github: https://github.com/kdexd/virtex
Paper: arxiv.org/abs/2006.06666
293 404
Deploy a Machine Learning Pipeline to the Cloud Using a Docker Container
https://www.kdnuggets.com/2020/06/deploy-machine-learning-pipeline-cloud-docker.html
293 404
YOLOv5 is Here: State-of-the-Art Object Detection at 140 FPS
Realtime object detection is improving quickly. The rate of improvement is improving even more quickly. The results are stunning.
https://blog.roboflow.ai/yolov5-is-here/
Github: https://github.com/ultralytics/yolov5
GCP Quickstart: https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart
293 404
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Github: https://github.com/implus/GFocal
Paper: https://arxiv.org/abs/2006.04388v1
293 404
PEGASUS: A State-of-the-Art Model for Abstractive Text Summarization
https://ai.googleblog.com/2020/06/pegasus-state-of-art-model-for.html
Github: https://github.com/google-research/pegasus
Paper: https://arxiv.org/abs/1912.08777
293 404
Part 2: Fast, scalable and accurate NLP: Why TFX is a perfect match for deploying BERT
https://blog.tensorflow.org/2020/06/part-2-fast-scalable-and-accurate-nlp.html
Code: https://colab.research.google.com/github/tensorflow/workshops/blob/master/blog/TFX_Pipeline_for_Bert_Preprocessing.ipynb
293 404
Introducing Neuropod, Uber ATG’s Open Source Deep Learning Inference Engine
Neuropod makes it easy for researchers to build models in a framework of their choosing while also simplifying productionization of these models.
It currently supports TensorFlow, PyTorch, TorchScript, and Keras.
https://eng.uber.com/introducing-neuropod/
Github: https://github.com/uber/neuropod
Neuropod Tutorial: https://neuropod.ai/tutorial/
293 404
A Scalable and Cloud-Native Hyperparameter Tuning System
Katib is a Kubernetes-based system for Hyperparameter Tuning and Neural Architecture Search. Katib supports a number of ML frameworks, including TensorFlow, Apache MXNet, PyTorch, XGBoost, and others.
Github: https://github.com/kubeflow/katib
Getting started with Katib: https://www.kubeflow.org/docs/components/hyperparameter-tuning/hyperparameter/
Paper: https://arxiv.org/abs/2006.02085v1
293 404
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Recursive Feature Pyramid implements thinking twice at the macro level, where the outputs of FPN are brought back to each stage of the bottom-up backbone through feedback connections
Github: https://github.com/joe-siyuan-qiao/DetectoRS
Paper: https://arxiv.org/abs/2006.02334v1
293 404
Introduction to Convolutional Neural Networks
The article focuses on explaining key components in CNN and its implementation using Keras python library.
https://www.kdnuggets.com/2020/06/introduction-convolutional-neural-networks.html
293 404
A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty
In this work presented a novel symmetric matrix representation of rotations that is singularity-free and requires marginal computational overhead
Website: https://papers.starslab.ca/bingham-rotation-learning/
Paper: https://arxiv.org/abs/2006.01031
Github: https://github.com/utiasSTARS/bingham-rotation-learn
293 404
Acme: A research framework for reinforcement learning
Acme strives to expose simple, efficient, and readable agents, that serve both as reference implementations of popular algorithms and as strong baselines, while still providing enough flexibility to do novel research
Github: https://github.com/deepmind/acme
Paper: https://arxiv.org/abs/2006.00979
293 404
Text Mining in Python: Steps and Examples
This blog summarizes text preprocessing and covers the NLTK steps including Tokenization, Stemming, Lemmatization, POS tagging, Named entity recognition and Chunking.
https://www.kdnuggets.com/2020/05/text-mining-python-steps-examples.html
