Available now! Telegram Research 2025 — the year's key insights 
Machine learning books and papers
Open in Telegram
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Show more📈 Analytical overview of Telegram channel Machine learning books and papers
Channel Machine learning books and papers (@machine_learn) in the English language segment is an active participant. Currently, the community unites 24 518 subscribers, ranking 8 048 in the Education category and 13 749 in the Iran region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 24 518 subscribers.
According to the latest data from 25 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by -164 over the last 30 days and by -1 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 7.13%. Within the first 24 hours after publication, content typically collects 1.90% reactions from the total number of subscribers.
- Post reach: On average, each post receives 1 748 views. Within the first day, a publication typically gains 465 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 1.
- Thematic interests: Content is focused on key topics such as disorder, psy, مقاله, framework, graph.
📝 Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
“Admin: @Raminmousa
ID: @Machine_learn
link: https://t.me/Machine_learn”
Thanks to the high frequency of updates (latest data received on 26 June, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Education category.
24 518
Subscribers
-124 hours
-407 days
-16430 days
Posts Archive
Compare NLP Transformer-based Models used for Sentiment Analysis code
🔺@Machine_learn
Adversarial_Training_to_improve_medical_diagnosis_robustness_in.pdf0.64 KB
Resource_efficient_medical_image_classification_for_edge_devices.pdf0.63 KB
Repost from Papers
سلام دوستان
ما دونفر از دانشجوی دکترای یکی از دانشگاه های تاپ آمریکا هستم.
خوش حالیم که اعلام کنیم مقالات قبلی ما اکسپت شد.
در حال حاضر جایگاههای نفرات در دو مقاله در حوزه کامپیوتر ساینس با موضوعات کوانتیزیشن، تفسیرپذیری و یادگیری بدون نظارت در زمینه پزشکی آزاد است.
بعد از سابمیت مقاله، پیپر، متن و کدهای مربوطه در اختیار شما قرار میگیرد. با تضمین چاپ مقاله توسط ما، میتونید برای اپلای دانشگاهها و گرینکارت اقدام بفرمایید.
همچنین با معرفی همکار یا نفرات قبلی، از تخفیف بهرهمند شوید.
لطفا در صورت تمایل به آی دی ما پیام دهید.
( پاسخ با اکانت قبلی ما به دلیل رمزورود به تلگرام امکان پذیر نیست)
آی دی جدید ما:
@rezaa_alvandi
A Brief Introduction to Neural Networks
📕 Book
@Machine_learn
Nexusflow released Athene v2 72B - competetive with GPT4o & Llama 3.1 405B Chat, Code and Math 🔥
> Arena Hard: GPT4o (84.9) vs Athene v2 (77.9) vs L3.1 405B (69.3)
> Bigcode-Bench Hard: GPT4o (30.8) vs Athene v2 (31.4) vs L3.1 405B (26.4)
> MATH: GPT4o (76.6) vs Athene v2 (83) vs L3.1 405B (73.8)
> Models on the Hub along and work out of the box w/ Transformers 🤗
https://huggingface.co/Nexusflow/Athene-V2-Chat
They also release an Agent model: https://huggingface.co/Nexusflow/Athene-V2-Agent
@Machine_learn
Repost from Papers
با عرض سلام
اگر از دوستان کسی توانایی گرفتن اکسپت برای مقاله زیر رو داره و توانایی پرداخت هزینه ی سرور رو داره به بنده پیام بده. اسم شخص به عنوان نفر ۴ در مقاله درج میشه.
Title: Transformer and XGBoost for time-series forecasting of Bitcoin prices using high-dimensional features
ABSTRACT: Bitcoin price prediction based on price indicators has become a hot field of study. In this article, Bitcoin price prediction is discussed based on hash rate features. For this purpose, a series of price indices were used in the beginning and the selection of features was done among 20 features. On the other hand, the selection of features was also done on the raw data of eight rates. This research used forecasting for one, seven, thirty and ninety days. In the classification based on raw features, the highest accuracy is 81%, and for a 90-day interval, on the other hand, the lowest RMSE value is 1.85, which is for a one-day interval. In the classification based on the features extracted from the indicators, the highest accuracy is 73% for the 90-day interval and the lowest RMSE is 1.58 for the 1-day interval.
@Raminmousa
@Machine_learn
Collection of resources in the form of eBooks related to Data Science, Machine Learning, and similar topics
📖 Github
@Machine_learn
Deep Learning and Computational Physics - Lecture Notes, University of South California
📓 book
@Machine_learn
با عرض سلام خيلي از دوستان در رابطه با طراحي صفر تا صد پروژه هاي ديپ از بنده سوال پرسيدن داخل پك زير ٣٦ پروژه رو با جزئيات شرح دادم:
1-Deep Learning Basic
-01_Introduction
--01_How_TensorFlow_Works
2-Classification apparel
-Classification apparel double capsule
-Classification apparel double cnn
3-ALZHEIMERS USING CNN(ResNet)
4-Fake News (Covid-19 dataset)
-Multi-channel
-3DCNN model
-Base line+ Char CNN
-Fake News Covid CapsuleNet
5-3DCNN Fake News
6-recommender systems
-GRU+LSTM MovieLens
7-Multi-Domain Sentiment Analysis
-Dranziera CapsuleNet
-Dranziera CNN Multi-channel
-Dranziera LSTM
8-Persian Multi-Domain SA
-Bi-GRU Capsule Net
-Multi-CNN
9-Recommendation system
-Factorization Recommender, Ranking Factorization Recommender, Item Similarity Recommender (turicreate)
-SVD, SVD++, NMF, Slope One, k-NN, Centered k-NN, k-NN Baseline, Co-Clustering(surprise)
10-NihX-Ray
-optimized CNN on FullDataset Nih-Xray
-MobileNet
-Transfer learning
-Capsule Network on FullDataset Nih-Xray
دوستاني كه نياز به اين پروژه ها دارن ميتونن با بنده در ارتباط باشن.
@Raminmousa
@Machine_learn
✅ کانال دانشکده مهندسی کامپیوتر دانشگاه صنعتی شریف 🔹⬇️⬇️⬇️⬇️
https://t.me/CEinUse
برای کنکور ارشد کمک نیاز به کمک داری ؟
نمیدونی برای دروس کنکور ارشدت کدوم استاد بهتره ؟
میخوای از تجربه دوستات و ترم بالاییا استفاده کنی؟
💯نمونه سوال و جزوه رو لازم داری ؟
https://t.me/CEinUse
همراه با فعالترین و پر عضوترین گروه دانشکده مهندسی کامپیوتر دانشگاه شریف
✌️ با حضور امیررضا آبانی رتبه ۹۰ کنکور ارشد مهندسی کامپیوتر
جوین شو که جزوه و کتاب نیازت میشه😁👇👇
https://t.me/CEinUse
https://t.me/CEinUse
https://t.me/CEinUse
Repost from Papers
💠Title:BERTCaps: BERT Capsule for persian Multi-domain Sentiment Analysis.
🔺Abstract:
Sentiment classification is widely known as a domain-dependent problem. In order to learn an accurate domain-specific sentiment classifier, a large number of labeled samples are needed, which are expensive and time-consuming to annotate. Multi-domain sentiment analysis based on multi-task learning can leverage labeled samples in each single domain, which can alleviate the need for large amount of labeled data in all domains. In this article, the purpose is BERTCaps to provide a multi-domain classifier. In this model, BERT was used for Instance Representation and Capsule was used for instance learning. In the evaluation dataset, the model was able to achieve an accuracy of 0.9712 in polarity classification and an accuracy of 0.8509 in domain classification.
journal: https://www.sciencedirect.com/journal/array
If:2.3
جايگاه ٤ اين مقاله رو نياز داريم.
دوستاني كه مايل به شركت هستن مي تونن به ايدي بنده پيام بدن.
@Raminmousa
@Paper4money
@Machine_learn
FRONTIERMATH: A BENCHMARK FOR EVALUATING ADVANCED
MATHEMATICAL REASONING IN AI
📚 Read
💠@Machine_learn
دوستانی که نیاز به این مقاله دارند تا امشب وقت باقی مانده است.
@Raminmousa
DeepArUco++: improved detection of square fiducial markers in challenging lighting conditions
🖥 Github: https://github.com/avauco/deeparuco
📕 Paper: https://arxiv.org/pdf/2411.05552v1.pdf
⚡️ Dataset: https://paperswithcode.com/dataset/coco
@Machine_learn
