I Compressed Bad Apple into a 3MB Neural Network [P] https://redd.it/1vfrco1 @datascientology

Channel
Data Scientology
@datascientology
On this record: Topic · Growth · Engagement · Posts · Citations · Cite this entry
1,139subscribers
-14 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 | -1001076468917 |
|---|---|
| Type | Channel |
| Username | @datascientology |
| Created | 21 September 2016 — measured — cross-checked against a third-party dataset (ext.tg_channel) |
| First recorded | 6 August 2026 |
| Last confirmed live | 18 November 2026 |
| Measurements held | 21 |
| Confirmed unchanged | 1 time, most recently 18 November 2026 |
| On Telegram | t.me/datascientology |
Topic
Technology — a classification, not a measurement. An on-box language model (Qwen3.6-35B-A3B-FP8, prompt version 1) read this channel’s own recent posts on 18 September 2026 and assigned it the closest of 31 fixed categories, at 98% confidence. This is a model’s judgement about what the channel is likely to be about, not a fact this register measured the way a subscriber count or a view count is measured — it can be revised on a later pass, and it carries no weight anywhere else on this page. How this classification works, and the other topics.
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 18 Nov 2026, 12:40 | 1,139 | +1 |
| 13 Nov 2026, 00:56 | 1,138 | -2 |
| 5 Nov 2026, 13:10 | 1,140 | +1 |
| 26 Oct 2026, 09:49 | 1,139 | -1 |
| 23 Oct 2026, 12:20 | 1,140 | -3 |
| 20 Oct 2026, 14:41 | 1,143 | -1 |
| 17 Oct 2026, 17:01 | 1,144 | -1 |
| 11 Oct 2026, 15:22 | 1,145 | -2 |
| 5 Oct 2026, 10:36 | 1,147 | +1 |
| 27 Sept 2026, 01:18 | 1,146 | -2 |
| 17 Sept 2026, 14:58 | 1,148 | +1 |
| 13 Sept 2026, 06:39 | 1,147 | -2 |
| 4 Sept 2026, 04:39 | 1,149 | +2 |
| 1 Sept 2026, 04:44 | 1,147 | -2 |
| 28 Aug 2026, 22:45 | 1,149 | -1 |
| 26 Aug 2026, 01:39 | 1,150 | -1 |
| 22 Aug 2026, 19:34 | 1,151 | -1 |
| 12 Aug 2026, 03:42 | 1,152 | -2 |
| 9 Aug 2026, 08:51 | 1,154 | +1 |
| 6 Aug 2026, 09:06 | 1,153 | first reading |
Engagement
17 posts held, back to 24 June 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of 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 17 posts for this entry, the most recent from 5 August 2026. An engagement rate over an empty window would be a number about nothing.
Recent posts
Is it too late regain some coherence in the ML research space in our life time? D Was just looking at the list of preprints on Arxiv cs.LG https://arxiv.org/list/cs.LG/recent?skip=0&show=500 Everyday 100 - 400 new machine learning papers gets uploaded on this server. Looking at this unending list of preprints is as if you stepped into a crowded room, like the stock trading floor on wall st. in the 1980s. Everyone…
Beginner here: My pothole detection model mistakes the roadside for potholes. https://redd.it/1v90113 @datascientology
30+ officially free AI/ML books, all in one curated repo https://redd.it/1v7cvqr @datascientology
Are there some textbooks that take a primarily engineering approach to machine learning (as opposed to a "scientific" approach)? D As someone who studied stats undergrad and industrial engineering operations research grad, and who thinks about the practical business of ML components in software.... I get lost and a bit hopeless when I think about how to make useful software out of ML models in a reasonable amount o…
SenseNova-Vision is open-sourced: handle every CV task as unified multimodal generation https://redd.it/1uyorje @datascientology
I reviewed that boy. https://redd.it/1uwsmbo @datascientology
Prompt-engineering paper accepted to ICML R "Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity" This paper was accepted to ICML this year. Its main idea is a very simple prompt-engineering trick: "changing the prompt this way led to more diverse sampling". Naturally, it is difficult to provide a rigorous theoretical analysis for something like this. Even if it works, I’m not sure this kin…
Hyperparameter tuning approach question R I am doing some work with cell type classification, where I have 4.3 million cells and 512 features (condensed embeddings from the encoder of a transformer). The broader goal is to implement a contextual bandit for augmenting the training set of the dataset, as it is currently imbalanced, and rare cell type classification is poor when I tried a baseline logistic regression …
TorchJD: Training with multiple losses in PyTorch P Hi everyone! I wanted to share some recent progress on TorchJD that might be useful to the machine learning community. When training models with multiple losses (multiple tasks, constraints, auxiliary losses, regularization terms, etc.), you typically have two options: Scalarization: Various ways to combine those losses into a single loss (e.g. average them or c…
I trained a local AI model that generated 22,000+ novel drug-like molecules — verified against 4.6M known compounds. Dataset available. Built an 80M parameter causal transformer on consumer hardware (RTX 5070), trained on MOSES + ZINC-250k. Generated and filtered for QED ≥ 0.5, SA ≤ 4.0, MW ≤ 500. Top compound hits QED 0.947. 100% novel against MOSES, ZINC, and ChEMBL. HuggingFace: https://huggingface.co/datasets/M…
Books/Resources to improve mathematical foundations for ML research D I am a mid to late stage PhD student in ML. I've known this before, but only recently I started feeling this urgently: my mathematical foundations are shaky, because I kept "learning-things-as-I-go" when working on various problems. I likely have only a year or two left until I graduate, and before I do so, I want to really dedicate some time and …
Showing the 12 most recent of 17 posts we hold for @datascientology. 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.
Mentions
Named by 8 registered channels — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
@IngressPrimeFeedback · 321 postOctober Strike
@OctoberStrike · 71 postr/badcode
@r_badcode · 391 postr/Furrypasta
@r_furrypasta · 301 postr/GharKeKalesh
@r_gharkekalesh · 691 postI'm going to hell for this
@r_imgoingtohellforthis · 1241 post@r_invites
@r_invites · 1831 postRussianIsSoHard
@RussianIsSoHard · 61 post
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 18 November 2026 — this entry's latest reading, not the date you are reading this.
“Data Scientology” (@datascientology), 1,139 subscribers as measured 18 November 2026. Telegram Register, tgregister.com/channel/datascientology.
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.