Endi mavjud! Telegram Tadqiqoti 2025 — yilning asosiy insaytlari 
Machine learning books and papers
Kanalga Telegram’da o‘tish
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Ko'proq ko'rsatish📈 Telegram kanali Machine learning books and papers analitikasi
Machine learning books and papers (@machine_learn) Ingliz til segmentidagi kanali faol ishtirokchi. Hozirda hamjamiyat 24 499 obunachidan iborat bo'lib, Taʼlim toifasida 8 053-o'rinni va Eron mintaqasida 13 774-o'rinni egallagan.
📊 Auditoriya ko‘rsatkichlari va dinamika
невідомо sanasidan buyon loyiha tez o‘sib, 24 499 obunachiga ega bo‘ldi.
30 Iyun, 2026 dagi oxirgi ma’lumotlarga ko‘ra kanal barqaror faollikka ega. Oxirgi 30 kunda obunachilar soni -131 ga, so‘nggi 24 soatda esa -4 ga o‘zgardi va umumiy qamrov yuqori darajada qolmoqda.
- Tasdiqlash holati: Tasdiqlanmagan
- Jalb etish (ER): Auditoriya o‘rtacha 7.24% darajada jalb etiladi. Nashrdan keyingi dastlabki 24 soatda kontent odatda umumiy obunachilar sonining 1.98% ini tashkil etuvchi reaksiyalarni to‘playdi.
- Post qamrovi: Har bir post o‘rtacha 1 773 marta ko‘riladi; birinchi sutkada odatda 484 ta ko‘rish yig‘iladi.
- Reaksiyalar va o‘zaro ta’sir: Auditoriya faol: har bir postga o‘rtacha 1 ta reaksiya keladi.
- Tematik yo‘nalishlar: Kontent disorder, psy, مقاله, framework, graph kabi asosiy mavzularga jamlangan.
📝 Tavsif va kontent siyosati
Muallif resursni shaxsiy fikrni ifoda etish maydoni sifatida ta’riflaydi:
“Admin: @Raminmousa
ID: @Machine_learn
link: https://t.me/Machine_learn”
Yuqori yangilanish chastotasi (oxirgi ma’lumot 01 Iyul, 2026 da olingan) sababli kanal doimo dolzarb va katta qamrovli bo‘lib qoladi. Analitika auditoriya kontent bilan faol hamkorlik qilishini, uni Taʼlim toifasidagi muhim ta’sir nuqtasiga aylantirishini ko‘rsatadi.
24 499
Obunachilar
-424 soatlar
-187 kunlar
-13130 kunlar
Postlar arxiv
با عرض سلام دوستانی که می خواهند در مقاله ی بالا شرکت کنند می تونن به ایدی بنده جهت اسم نویسی پیام بدن نفر اول 500$ و نفر دوم 400$ جهت مشارکت. با تشکر
@Raminmousa
Sentiment analysis (SA) is a computational analysis of ideas, feelings and opinions, and uses natural language processing techniques, computational techniques and text analyses to extract polarity (positive, negative or neutral) from non-structured documents or textual comments. the purpose of the multi-domain SA is that the classifier training is based on a set of labelled data in a way that reduces the need for large amounts of data on specific domains and to address the challenges of data scarcity in them with the help of existing data on other domains. The purpose of this paper is to present a new method for analysing the Persian multi-domain SA using DL approaches. The proposed Bi-GRUCapsule approach uses the combination of two networks Bi-GRU and CapsuleNet to solve the multi-domain SA problem that Bi-GRU has the role of extracting features for CapsuleNet. the proposed approach was evaluated using the Digikala dataset and has received acceptable accuracy compared to the existing approaches.
Algorithms for Clustering Data #Book #Clustering @Machine_learn
DATA CLUSTERING Algorithms and Applications #Clustering #Book @Machine_learn
Cluster Analysis: Basic Concept #Clustering #book @Machine_learn
📑 Extreme Zero-Shot Learning for Extreme Text Classification
Github: https://github.com/amzn/pecos
Paper: https://arxiv.org/abs/2112.08652v1
@Machine_learn
📑 Extreme Zero-Shot Learning for Extreme Text Classification
Github: https://github.com/amzn/pecos
Paper: https://arxiv.org/abs/2112.08652v1
@Machine_learn
Training Machine Learning Models More Efficiently with Dataset Distillation
http://ai.googleblog.com/2021/12/training-machine-learning-models-more.html
@Machine_learn
با عرض سلام دوستانی که نیاز به تهیه ی پکیچ ما دارند می تونن به ایدی بنده پیام بدن @Raminmousa . همچنین دوستانی که نیاز به مشاوره در رابطه با ابده های جدید ، کارهای عملی، پروپوزال و پایان نامه دارند می تونن با ایدی بنده یا شماره واتس اپ بنده 09333900804 در ارتباط باشند.
🕷 Bayesian Active Learning (BaaL)
Github: https://github.com/ElementAI/baal
Documentation: https://baal.readthedocs.io.
Paper: https://arxiv.org/abs/2112.06586v1
Blog: https://www.elementai.com/news/2019/element-ai-makes-its-bayesian-active-learning-library-open-source
@Machine_learn
🎓 GAN-Supervised Dense Visual Alignment
Github: https://github.com/wpeebles/gangealing
Project: https://www.wpeebles.com/gangealing
Paper: https://arxiv.org/abs/2112.04894v1
Dataset: https://paperswithcode.com/dataset/celeba
@Machine_learn
Movie Name Generation Using GPT-2
https://www.nbshare.io/notebook/976197999/Movie-Name-Generation-Using-GPT-2/
@Machine_learn
General and Scalable Parallelization for Neural Networks
http://ai.googleblog.com/2021/12/general-and-scalable-parallelization.html
@Machine_learn
Improving Vision Transformer Efficiency and Accuracy by Learning to Tokenize
http://ai.googleblog.com/2021/12/improving-vision-transformer-efficiency.html
@Machine_learn
A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents
Github: https://github.com/extreme-classification/deepxml
Paper: https://arxiv.org/abs/2111.06685v1
Dataset: https://paperswithcode.com/dataset/extreme-classification
@Machine_learn
🔹 LUMINOUS: Indoor Scene Generation for Embodied AI Challenges
Github: https://github.com/amazon-research/indoor-scene-generation-eai
Paper: https://arxiv.org/abs/2111.05527v1
Dataset: https://paperswithcode.com/dataset/ai2-thor
@Machine_learn
Deep Neural Networks to Detect Weeds from Crops in Agricultural Environments in Real-Time: A Review
Github: https://github.com/Ildaron/Laser_control
Paper: https://www.mdpi.com/2072-4292/13/21/4486
@Machine_learn
Deep Learning for disentangling Liquidity-constrained and Strategic Default #DL #Liquidity #Paper @Machine_learn
