¡Ya disponible! Investigación de Telegram 2025 — los principales insights del año 
Machine learning books and papers
Ir al canal en Telegram
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Mostrar más📈 Análisis del canal de Telegram Machine learning books and papers
El canal Machine learning books and papers (@machine_learn) en el segmento lingüístico de Inglés es un actor destacado. Actualmente la comunidad reúne a 24 610 suscriptores, ocupando la posición 8 079 en la categoría Educación y el puesto 13 665 en la región Irán.
📊 Métricas de audiencia y dinámica
Desde su creación el невідомо, el proyecto ha mostrado un crecimiento acelerado, reuniendo a 24 610 suscriptores.
Según los últimos datos del 03 junio, 2026, el canal mantiene una actividad estable. En los últimos 30 días la variación de miembros fue de -179, y en las últimas 24 horas de -8, conservando un alto alcance.
- Estado de verificación: No verificado
- Tasa de interacción (ER): El promedio de interacción de la audiencia es 15.04%. Durante las primeras 24 horas tras publicar, el contenido suele obtener 2.54% de reacciones respecto al total de suscriptores.
- Alcance de las publicaciones: Cada publicación recibe en promedio 0 visualizaciones. En el primer día suele acumular 625 visualizaciones.
- Reacciones e interacción: La audiencia responde de forma activa: el promedio de reacciones por publicación es 0.
- Intereses temáticos: El contenido se centra en temas clave como disorder, psy, مقاله, framework, graph.
📝 Descripción y política de contenido
El autor describe el recurso como un espacio para expresar opiniones subjetivas:
“Admin: @Raminmousa
ID: @Machine_learn
link: https://t.me/Machine_learn”
Gracias a la alta frecuencia de actualizaciones (últimos datos recibidos el 04 junio, 2026), el canal mantiene la vigencia y un amplio alcance. La analítica demuestra que la audiencia interactúa activamente con el contenido, lo que lo convierte en un punto de referencia dentro de la categoría Educación.
24 610
Suscriptores
-824 horas
-737 días
-17930 días
Archivo de publicaciones
+5
🎬 ساخت ویدیو
• Sora
• Kling
• Veo
• Seedance
• Lumalabs
🎨 ساخت تصویر
• Google Flow
• Qwen Image
• NanoBanana
• ChatGPT Image
• Grok
🎤 تقلید صدا
• ElevenLabs
• Fish Audio
• Minimax
• Descript
• Respeecher
🧠 تحقیق و کاوش
• ChatGPT
• Gemini
• Perplexity
• NotebookLM
• Deepseek
🗣 ساخت کاراکتر سخنگو
• Heygen
• Synthesia
• D-ID
• Hedra
━━━━━━━━━━━━━━━
🔗 لینک ابزارها:
• ChatGPT → https://chatgpt.com
• Gemini → https://gemini.google.com
• Perplexity → https://perplexity.ai
• Deepseek → https://deepseek.com
• NotebookLM → https://notebooklm.google.com
• Kling → https://klingai.com
• Veo → https://deepmind.google/technologies/veo
• Lumalabs → https://lumalabs.ai
• Sora → https://openai.com/sora
• ElevenLabs → https://elevenlabs.io
• Fish Audio → https://fish.audio
• Descript → https://descript.com
• Heygen → https://heygen.com
• Synthesia → https://synthesia.io
• D-ID → https://d-id.com
@ai_farshad
برای این مقاله فقط ۵ روز وقت داریم دوستانی که نیاز دارند زودتر اقدام کنن...!
با عرض سلام یکی از مقالاتمون در حوزه ی wound image classification در ژورنال nature scientific reports ریوایزد خورده و جایگاه های ۲، ۴ و ۵ اش قابل اضافه شدن می باشد. دوستانی که نیاز دارن می تونن جهت ثبت اسم به ایدی بنده پیام بدن
Price
2: 300$
4: 200$
5:150$
@Raminmousa
@Paper4money
@Machine_learn
Repost from Papers
با عرض سلام یکی از مقالاتمون در حوزه ی wound image classification در ژورنال nature scientific reports ریوایزد خورده و جایگاه های ۲، ۴ و ۵ اش قابل اضافه شدن می باشد. دوستانی که نیاز دارن می تونن جهت ثبت اسم به ایدی بنده پیام بدن
Price
2: 300$
4: 200$
3:150$
@Raminmousa
@Paper4money
@Machine_learn
Repost from Machine Learning with Python
Follow the Machine Learning with Python channel on WhatsApp: https://whatsapp.com/channel/0029VaC7Weq29753hpcggW2A
🔥 Awesome open-source project to learn more about Transformer Models! 🤖✨
We found this interactive website that shows you visually how transformer models work. 🌐📊
Transformer Explainer:
https://poloclub.github.io/transformer-explainer/
@Machine_learn
با عرض سلام
دوستان اوضاع اصلا جالب نیست و کلا اینترنت نداریم. امیدوارم حالتون خوب باشه و اوضاع بهتر بشه.
🖤
Fri, 27 Feb 2026 (showing first 50 of 206 entries )
[1] arXiv:2602.23352 [pdf, html, other]
Stark localization of interacting particles
Wojciech De Roeck, Amirali Hannani, Alessio Lerose, Nathan Vandenbosch
Subjects: Mathematical Physics (math-ph); Disordered Systems and Neural Networks (cond-mat.dis-nn)
[2] arXiv:2602.23350 [pdf, html, other]
A strengthening of the dimensional Brunn-Minkowski conjecture implies the (B)-Conjecture
Sotiris Armeniakos, Jacopo Ulivelli
Comments: Comments are welcome!
Subjects: Functional Analysis (math.FA); Metric Geometry (math.MG)
[3] arXiv:2602.23343 [pdf, html, other]
Cyclic sieving for a class of rectangular domino tableaux
Laura Colmenarejo, Bridget Eileen Tenner, Camryn E. Thompson
Comments: 17 pages
Subjects: Combinatorics (math.CO)
[4] arXiv:2602.23340 [pdf, html, other]
Combinatorial Properties of the Raisonnier Filter
Spyridon Dialiatsis, Yurii Khomskii
Subjects: Logic (math.LO)
[5] arXiv:2602.23326 [pdf, html, other]
Spin Glass Concepts in Computer Science, Statistics, and Learning
Andrea Montanari
Comments: 33 pages; 2 pdf figures
Subjects: Probability (math.PR); Disordered Systems and Neural Networks (cond-mat.dis-nn)
[6] arXiv:2602.23325 [pdf, html, other]
Spanning tight components in 4-uniform hypergraphs
Francesco Di Braccio, Brian Hearn, Joanna Lada, Mihir Neve, Lu-Ming Zhang
Comments: 24 pages, 4 figures
Subjects: Combinatorics (math.CO)
[7] arXiv:2602.23323 [pdf, html, other]
Modeling Large-Scale Adversarial Swarm Engagements using Optimal Control
Claire Walton, Isaac Kaminer, Qi Gong, Abram H. Clark, Theodoros Tsatsanifos
Comments: arXiv admin note: substantial text overlap with arXiv:2108.02311. substantial text overlap with arXiv:2108.02311
Subjects: Optimization and Control (math.OC)
@Machine_learn
✨RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning
📝 Summary:
RoboCurate enhances synthetic robot learning data by evaluating action quality through simulator replay consistency. It also augments observation diversity via image editing and video transfer techniques. This leads to substantial improvements in robot task success rates compared to using real da...
🔹 Publication Date: Published on Feb 21
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.18742
• PDF: https://arxiv.org/pdf/2602.18742
• Project Page: https://seungkukim.github.io/robocurate/
@Machine_learn
Repost from Papers
با عرض سلام مي خواهيم مقاله كنفرانسي با عنوان زير بنويسيم
Complex Sig: Complex deep model for signal classification
Abstract: The ability to classify signals is an important task that provides the opportunity for many different applications. In the early research for signal classification, they had to
decompose the signal using FT (Fourier transform), SIFT, MFCC or other manual methods using statistical modulation features, then classify these signals by a traditional machine learning approach. In the last few years, the process of learning deep models that lead to the automatic extraction of features has positively affected classification. Different deep-learning models with di erent depths have been proposed in the literature.
This article proposes different approaches to classify signals in different SNR conditions. ResNet-based approaches perform well for high SNRs but poorly when dealing with low SNRs. Therefore, TRansforme-based approaches were proposed for classification, reaching an average accuracy of 0.7056 in low SNR and an average of 0.9089 in high SNR.
نتايج اوليه خوب بوده و قابل مقايسه با ساير مقالات تو اين حوزه ميباشد. نياز به ٢ يا سه نفر داريم كه مشاركت كنند.
Price:
2: 300$
3:200$
4:100$
@Raminmousa
@paper4money
@Machine_learn
هر ثانیه توقف، یعنی از دست رفتن زمان، هزینه و فرصت…
پایداری دیگر یک انتخاب نیست؛ یک ضرورت است.
🚀 ایرانGPU؛جایی که پروژهها متوقف نمیشوند.
🏛 تنها و اولین شرکت بورسی هوش مصنوعی ایران
🕒 بیش از ۵ سال سابقه فعالیت حرفهای
🌐 شبکهای از ۲۰+ دیتاسنتر غیرمتمرکز در سراسر کشور
🧠 مناسب تیمها، پژوهشگران و سازمانهای حرفهای AI
🛟 پشتیبانی ۲۴ ساعته، ۷ روز هفته
📈 تضمین SLA با دسترسپذیری 99.9٪ و ارائه سرور داخل ایران
📩 ثبت درخواست مشاوره | شروع مسیر هوشمندانه
https://b2n.ir/qk8423
🔹 Title: Predicting the Order of Upcoming Tokens Improves Language Modeling
🔹 Publication Date: Published on Aug 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19228
• PDF: https://arxiv.org/pdf/2508.19228
• Github: https://github.com/zaydzuhri/token-order-prediction
@Machine_learn
🔹 Title: CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
🔹 Publication Date: Published on Aug 27
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.20096
• PDF: https://arxiv.org/pdf/2508.20096
• Project Page: https://github.com/OpenIXCLab/CODA
• Github: https://github.com/OpenIXCLab/CODA
@Machine_learn
Dataset Name: Gallstone Dataset (UCI)
Basic Description: Gallstone Dataset (UCI Machine Learning Repository)
📥 DATASET DOWNLOAD INFORMATION
==================================
🔴 Dataset Size: Download dataset as zip (81 kB)
🔰 Direct dataset download link:
URL not found
📊 Additional information:
==================================
File count not found
Views: 1,128
Downloads: 246
📚 RELATED NOTEBOOKS:
==================================
1. Heart Attack Risk Prediction Dataset | Upvotes: 274
URL: https://www.kaggle.com/datasets/iamsouravbanerjee/heart-attack-prediction-dataset
@Machine_learn
How we made Python's packaging library 3x faster
📚 Read
@Machine_learn
با عرض سلام برای مقاله زیر نیاز به نفرات ۲ و ۳ داریم.
KG-Psy: A Knowledge-Graph and GPT-5 Based Framework for Personalized Clinical Decision Support in Bipolar Disorder and Borderline Personality Disorder
Abstract: Accurate diagnosis and personalized treatment planning for complex psychiatric disorders such as Bipolar Disorder (BD) and Borderline Personality Disorder (BPD) remain major challenges due to overlapping symptoms, fluctuating mood patterns, and heterogeneous clinical presentations. To address these challenges, we introduce KG-Psy, a hybrid neuro-symbolic framework that combines a domain-specific psychiatric Knowledge Graph (KG) with the advanced reasoning capabilities of GPT-5.
KG-Psy constructs multi-layer psychiatric knowledge graphs encoding symptom trajectories, neural correlates, pharmacological mechanisms, therapeutic guidelines, comorbidities, and behavioral patterns extracted from large-scale clinical literature. GPT-5 is employed to extract clinical entities, infer latent symptom-neural relationships, assess diagnostic likelihoods, and generate patient-specific treatment recommendations. The integration of structured KG reasoning with LLM-based inference allows KG-Psy to produce interpretable, evidence-supported, and clinically actionable outputs.
We evaluated KG-Psy on 310 de-identified psychiatric case reports and 12 expert-validated benchmark scenarios. The framework achieved 91.5% F1-score in distinguishing BD from BPD and an average pathway confidence of 86.9%, indicating robust multi-step inference. In personalized treatment recommendation tasks, KG-Psy achieved 88.7% accuracy, outperforming LLM-only and KG-only baselines by 23% and 31%, respectively.
....
Keywords: Bipolar Disorder, Borderline Personality Disorder, Knowledge Graph, GPT-5, Personalized Treatment
2 :20 milion
3 :15 milion
@Raminmousa
@Machine_learn
@paper4money
