Telegram RegisterThe public register of Telegram

Channel

TensorFlow

@tensorflowblog

On this record: Growth · Engagement · Posts · Citations · Cite this entry

1,354subscribers

+0 since we began measuring on 6 August 2026

Risers and fallers across the register · movement among entries of 1,000–3,162.

Register entry

Telegram ID-1001433448917
TypeChannel
Username@tensorflowblog
Created3 October 2020measured — cross-checked against a third-party dataset (TGDataset)
First recorded6 August 2026
Last confirmed live12 August 2026
Measurements held4
Confirmed unchanged1 time, most recently 12 August 2026
On Telegramt.me/tensorflowblog

Growth

1,3541,3551,354.56 August 2026 — 1,354 subscribers6 August 2026 — 1,354 subscribers9 August 2026 — 1,355 subscribers12 August 2026 — 1,354 subscribers6 August 202612 August 2026
4 measurements spanning 6 days. Dots are measurements; the straight line between them is drawn to join them, not to claim we know the path taken in between — snapshots are recorded only when a count changes, so gaps mean “no change observed”, never “interpolated”. The vertical axis spans 1,354–1,355 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
12 Aug 2026, 18:181,354-1
9 Aug 2026, 23:361,355+1
6 Aug 2026, 20:311,354no change
6 Aug 2026, 20:281,354first reading

Engagement

16 posts held, back to 3 February 2024the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 pageof Telegram’s post history, 20 posts per page.

Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 16 posts for this entry, the most recent from 7 April 2025. An engagement rate over an empty window would be a number about nothing.

Recent posts

7 Apr 2025, 12:50 UTC≈1,910 viewsread 6 August 2026
Photo

🔎 Alibi Detect — библиотека, которая замечает подозрительные изменения в поведении входных данных или предсказаний у ML моделей. Проект довольно универсален — он работает с табличными данными, текстами, изображениями и временными рядами, поддерживая как TensorFlow, так и PyTorch. Особенно ценно, что система умеет ловить не только очевидные выбросы, но и едва заметные изменения в распределениях. 🤖 GitHub

24 Feb 2025, 19:09 UTC≈1,880 viewsread 6 August 2026
Forwarded from @ai_machinelearning_big_dataPhoto

⚡️ EasyR1 – эффективный и масштабируемый фреймворк для обучения с подкреплением (RL) с поддержкой мультимодальных данных. Чем интересен EasyR1? EasyR1 сочетает в себе алгоритм GRPO, продемонстрированный в DeepSeek R1, и расширение системы veRL для поддержки vision-language моделей, таких как Qwen2.5-VL. Уже после 30 шагов обучения фреймворк показал прирост производительности на 5% в экспериментах на тестовом наборе

15 Feb 2025, 15:02 UTC≈1,500 viewsread 6 August 2026
Video

🧠 Разбираем Функцию Радемахера. Машинное обучение Курс математики - Видео - Урок 1 / Урок2 / Урок3 / Урок4 / Урок5 / - Урок6/ Урок7/ Урок8 / Урок9 - Colab -Полный курс

24 Jan 2025, 02:24 UTC≈1,560 viewsread 6 August 2026
Photo

CUDA 12.8 just dropped with Blackwell support. TensorCore 5th Generation Family Instructions: https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#tensorcore-5th-generation-instructions

30 Dec 2024, 15:33 UTC≈1,680 viewsread 6 August 2026
Video

⚡️ Введение в тензорные сети 📌 Видео 📌 Урок 1 / Урок2 / Урок3 / Урок4 / Урок5 📌 Colab @tensorflowblog

14 Dec 2024, 16:19 UTC≈1,740 viewsread 6 August 2026
Video

🔥 Курс Математика Машинного обучения: Что такое тензоры. 📌 Видео 📌Colab с кодом @tensorflowblog

11 Sept 2024, 19:01 UTC≈2,420 viewsread 6 August 2026
Forwarded from @ai_machinelearning_big_dataPhoto

🌟SALSA: Стабильная адаптация линейного поиска Armijo. SALSA (Stable Armijo Line Search Adaptation) — метод, разработанный для оптимизации Learning Rate (LR) во время обучения. Основная концепция метода построена вокруг выполнения линейного поиска для определения наилучшего возможного LR для каждого шага обучения, что дает быструю сходимость и улучшенное обобщение. Чтобы уменьшить вычислительную нагрузку, Salsa пред

2 May 2024, 06:49 UTC≈2,400 viewsread 6 August 2026
Forwarded from @data_analysis_mlVideo

💨 Scaling hierarchical agglomerative clustering to trillion-edge graphs Кластеризация графов объединяет похожие элементы в группы, что помогает лучшему понять взаимосвязи в данных. В этой статье инженеры Google рассказывают о ключевых методах, которые позволили им построить мощнейший алгоритм, позволяющий группировать графы с триллионами ребер. https://research.google/blog/scaling-hierarchical-agglomerative-clus

9 Apr 2024, 16:58 UTC≈2,230 viewsread 6 August 2026

https://blog.tensorflow.org/2024/04/faster-dynamically-quantized-inference-with-xnnpack.html @tensorflowblog

29 Mar 2024, 08:03 UTC≈2,220 viewsread 6 August 2026
Photo

⚡️ AutoBNN: Probabilistic time series forecasting with compositional bayesian neural networks Autobahn сочетает интерпретируемость традиционных вероятностных подходов с масштабируемостью и гибкостью нейронных сетей для построения сложных моделей прогнозирования временных рядов с использованием сложных данных. Узнайте больше и попробуйте готовый код → https://blog.research.google/2024/03/autobnn-probabilistic-time-s

16 Mar 2024, 09:27 UTC≈2,330 viewsread 6 August 2026

SOTA lowbit LLM quantization INT8FP8INT4FP4NF4 sparsity leading model compression techniques on TensorFlow PyTorch and ONNX Runtime View on Github.com

14 Mar 2024, 10:04 UTC≈1,750 viewsread 6 August 2026

https://blog.tensorflow.org/2024/03/whats-new-in-tensorflow-216.html @tensorflowblog

Showing the 12 most recent of 16 posts we hold for @tensorflowblog. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.

Forward network

Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.

Mentions

A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.

Cite this entry

A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 12 August 2026 — this entry's latest reading, not the date you are reading this.

“TensorFlow” (@tensorflowblog), 1,354 subscribers as measured 12 August 2026. Telegram Register, tgregister.com/channel/tensorflowblog.

Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.