Telegram RegisterThe public register of Telegram
Telegram profile photo for Neural Networks Engineering

Channel

Neural Networks Engineering

@neural_network_engineering

On this record: Growth · Engagement · Reactions · Stars · Posts · Cite this entry

2,175subscribers

-1 since we began measuring on 7 August 2026

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

Register entry

Telegram ID-1001265535488
TypeChannel
Username@neural_network_engineering
CreatedBetween 1 March 2018 and 15 December 2020— estimated from Telegram’s id allocation, not measured. How this range is calculated.
First recorded7 August 2026
Last confirmed live26 August 2026
Measurements held6
Confirmed unchanged2 times, most recently 26 August 2026
On Telegramt.me/neural_network_engineering

Growth

2,1752,1782,176.57 August 2026 — 2,176 subscribers8 August 2026 — 2,176 subscribers13 August 2026 — 2,175 subscribers17 August 2026 — 2,177 subscribers20 August 2026 — 2,178 subscribers23 August 2026 — 2,175 subscribers7 August 202623 August 2026
6 measurements spanning 15 days, net -1. 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 2,175–2,178 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
23 Aug 2026, 09:232,175-3
20 Aug 2026, 03:352,178+1
17 Aug 2026, 10:332,177+2
13 Aug 2026, 23:372,175-1
8 Aug 2026, 01:212,176no change
7 Aug 2026, 22:462,176first reading

Engagement

20 posts held, back to 15 December 2020the 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 20 posts for this entry, the most recent from 23 February 2026. An engagement rate over an empty window would be a number about nothing.

Reaction mix

295 reactions across 17 posts, in 13 distinct kinds. The most used accounts for 36.6% of them.

Every reaction kind recorded on the sample, most used first
ReactionCountShareShare, drawn
👍10836.6%
🔥10334.9%
4515.3%
👏93.05%
😱72.37%
💯62.03%
🤡62.03%
20.678%
❤‍🔥20.678%
🏆20.678%
😁20.678%
🙏20.678%
👌10.339%

No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.

Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.

Coverage. Reactions were read on 17 of the 20 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 295reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.

Measured over the 20 most recent posts we hold, published 15 December 2020 to 23 February 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.

Telegram Stars

Stars received
4
across the posts below
Posts paid on
2
of 20 we hold a reading for · 10%
Most on one post
3
single highest reading

A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @neural_network_engineering. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.

Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.

This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.

Counted over the 20 most recent posts we hold for this entry, published 15 December 2020 to 23 February 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.

Recent posts

23 Feb 2026, 17:14 UTC≈1,010 views10 reactions3 Starsread 7 August 2026

​​Relevance Feedback Did you know that Google search results used to have 👍/👎 buttons? It was the way to collect signals from users and improve the ranking. Do you know why you don't see those buttons anymore? People are either too lazy to click or they abuse the buttons to their advantage. In 2026, however, real people don't have to rank raw search results anymore - there are all sorts of AI in the middle. And her

4🔥4👏2

Signed nne_controll_bot

9 Jun 2025, 12:03 UTC≈1,810 views16 reactionsread 7 August 2026

​​Embeddings Confidence Let's say we want to know which embeddings are good and which are noisy. Normally, you can't do this, because embedding model tries to represent the whole variety of objects. Even if input data is random, it would still match with similar random data. Using the score threshold is also not a good idea, embedding models were not trained to predict absolute scores, only relative scores makes s

13❤‍🔥2🙏1

Signed nne_controll_bot

8 Jun 2025, 13:52 UTCviews —20 reactionsread 7 August 2026

Posted without readable text

😱7🔥6🤡61

14 May 2025, 17:16 UTC≈1,990 views26 reactionsread 7 August 2026

​​MiniCOIL: Contextualized per-word embeddings We continue our experiments with unorthodox methods to embed texts. This time we want to solve the following problems of BM25: - It can't differentiate homonyms: "bat" as and animal and a baseball "bat" are the same thing for BM25. - It does loose the information during the stemming process: "information" and "informant" are the same for BM25. How are we doing this?

👍1210👌1💯1🔥1😁1

Signed nne_controll_bot

2 Jul 2024, 12:57 UTC≈3,650 views36 reactions1 Starread 7 August 2026

​​BM42: the next hybrid search baseline You probably heard that embedding similarity struggles with exact keyword matches, especially when the keyword is a rare word, a name, or some kind of ID. Usually, this problem is solved by combining the embedding similarity with an exact keyword search like BM25. However, BM25 relies on pure statistics and has no idea about the meaning of the words. This works well for larg

🔥19👍832🏆2💯2

Signed nne_controll_bot

23 Jan 2024, 10:22 UTC≈4,890 views33 reactionsread 7 August 2026

https://techcrunch.com/2024/01/23/qdrant-open-source-vector-database/ We are so hiring!

🔥21👏5👍32💯2

Signed Andrey

4 Dec 2023, 15:29 UTC≈5,250 views19 reactionsread 7 August 2026

Attention all Berliners! You are invited to our first offline meetup! Join us for talks on vector search, machine learning, and more. I will also be participating, providing an overview of Qdrant's progress and future plans. Still not convinced? We will have free pizza and beer! The event is scheduled for December 8, 2023, at 18:00, in Berlin. Please register https://lu.ma/vectorspace.

🔥14👍41

Signed Andrey

8 Aug 2023, 12:34 UTC≈6,100 views22 reactionsread 7 August 2026

Vector Similaruty beyond Search Vector similarity offers a range of powerful functions that go far beyond those available in traditional full-text search engines and the conventional kNN search. We just scratched the surface of the topic but already found a lot of new ways to interact with the data, including: - Dissimilarity search - that can be applied to anomaly detection, mislabeling detection, and data cleani

🔥15👍7

Signed nne_controll_bot

31 Aug 2022, 12:15 UTC≈8,570 views33 reactionsread 7 August 2026

​​How many layers to fine-tune? Model fine-tuning allows you to improve the quality of the pre-trained models with just a fraction of the resources spent on training the original model. But there is a trade-off between the number of layers you tune and the precision you get. Using fewer layers allows for faster training with a larger batch size, while more layers increase the model's capacity. We've done experiments

👍256😁1🙏1

Signed nne_controll_bot

29 Jun 2022, 11:46 UTC≈7,830 views13 reactionsread 7 August 2026
Video

One of the main features of the framework is caching. It allows you to infer large models only once and then use cached vectors during the training. It speeds up the process x100 times, simultaneously allowing you to use batch sizes that are unattainable in other ways. (gif)

👍11🔥2

Signed Andrey

29 Jun 2022, 11:45 UTC≈7,100 views14 reactionsread 7 August 2026

Similarity Learning lacks a framework. So we built one. Many general-purpose frameworks allow you to train Computer Vision or NLP tasks quickly. However, Similarity Learning has peculiarities, which usually require an additional layer of complexity on top of the usual pipelines. So, for example, the batch size in the training of similarity models has a much greater role than in other models. Labels either do not exi

🔥9👍4💯1

Signed Andrey

4 May 2022, 12:40 UTC≈6,470 views21 reactionsread 7 August 2026

Metric Learning for Anomaly Detection Anomaly detection is one of those tasks to which it is challenging to apply classical ML methods directly. The balancing of normal and abnormal examples and the internal inconsistency of anomalies make classifier training a challenging task. And the difficulty is often related to data labeling, which in the case of anomalies may not be trivial. The metric learning approach avo

🔥11👍82

Signed nne_controll_bot

Showing the 12 most recent of 20 posts we hold for @neural_network_engineering. 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.

Stars beside a post are paid reactions — Telegram Stars, bought with money and spent on that post. They are a different unit from reactions and are never added to them, here or anywhere else on this page.

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 23 August 2026 — this entry's latest reading, not the date you are reading this.

“Neural Networks Engineering” (@neural_network_engineering), 2,175 subscribers as measured 23 August 2026. Telegram Register, tgregister.com/channel/neural_network_engineering.

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.