Forwarded from Machine Learning with Python
Our Group on Signal (only for Programmers)
https://signal.group/#CjQKIPcpEqLQow53AG7RHjeVk-4sc1TFxyym3r0gQQzV-OPpEhCPw_-kRmJ8LlC13l0WiEfp
https://signal.group/#CjQKIPcpEqLQow53AG7RHjeVk-4sc1TFxyym3r0gQQzV-OPpEhCPw_-kRmJ8LlC13l0WiEfp
π€π§ DeepEyesV2: The Next Leap Toward Agentic Multimodal Intelligence
ποΈ 23 Nov 2025
π AI News & Trends
The evolution of artificial intelligence has reached a stage where models are no longer limited to understanding text or images independently. The emergence of multimodal AI systems capable of processing and reasoning across multiple types of data has transformed how machines interpret the world. Yet, most existing multimodal models remain passive observers, unable to act ...
#DeepEyesV2 #AgenticMultimodalIntelligence #MultimodalAI #AIEvolution #ActiveReasoning #AIAction
ποΈ 23 Nov 2025
π AI News & Trends
The evolution of artificial intelligence has reached a stage where models are no longer limited to understanding text or images independently. The emergence of multimodal AI systems capable of processing and reasoning across multiple types of data has transformed how machines interpret the world. Yet, most existing multimodal models remain passive observers, unable to act ...
#DeepEyesV2 #AgenticMultimodalIntelligence #MultimodalAI #AIEvolution #ActiveReasoning #AIAction
π The Machine Learning βAdvent Calendarβ Day 6: Decision Tree Regressor
π Category: MACHINE LEARNING
π Date: 2025-12-06 | β±οΈ Read time: 10 min read
During the first days of this Machine Learning Advent Calendar, we explored models based onβ¦
#DataScience #AI #Python
π Category: MACHINE LEARNING
π Date: 2025-12-06 | β±οΈ Read time: 10 min read
During the first days of this Machine Learning Advent Calendar, we explored models based onβ¦
#DataScience #AI #Python
π€π§ Reducing Hallucinations in Vision-Language Models: A Step Forward with VisAlign
ποΈ 24 Nov 2025
π AI News & Trends
As artificial intelligence continues to evolve, Large Vision-Language Models (LVLMs) have revolutionized how machines understand and describe the world. These models combine visual perception with natural language understanding to perform tasks such as image captioning, visual question answering and multimodal reasoning. Despite their success, a major problem persists β hallucination. This issue occurs when a ...
#VisAlign #ReducingHallucinations #VisionLanguageModels #LVLMs #MultimodalAI #AISafety
ποΈ 24 Nov 2025
π AI News & Trends
As artificial intelligence continues to evolve, Large Vision-Language Models (LVLMs) have revolutionized how machines understand and describe the world. These models combine visual perception with natural language understanding to perform tasks such as image captioning, visual question answering and multimodal reasoning. Despite their success, a major problem persists β hallucination. This issue occurs when a ...
#VisAlign #ReducingHallucinations #VisionLanguageModels #LVLMs #MultimodalAI #AISafety
β€1
π€π§ LEANN: The Bright Future of Lightweight, Private, and Scalable Vector Databases
ποΈ 24 Nov 2025
π AI News & Trends
In the rapidly expanding world of artificial intelligence, data storage and retrieval efficiency have become major bottlenecks for scalable AI systems. The growth of Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) has further intensified the demand for fast, private and space-efficient vector databases. Traditional systems like FAISS or Milvus while powerful, are resource-heavy and ...
#LEANN #LightweightVectorDatabases #PrivateAI #ScalableAI #RAG #AIDataStorage
ποΈ 24 Nov 2025
π AI News & Trends
In the rapidly expanding world of artificial intelligence, data storage and retrieval efficiency have become major bottlenecks for scalable AI systems. The growth of Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) has further intensified the demand for fast, private and space-efficient vector databases. Traditional systems like FAISS or Milvus while powerful, are resource-heavy and ...
#LEANN #LightweightVectorDatabases #PrivateAI #ScalableAI #RAG #AIDataStorage
β€1
π€π§ Omnilingual ASR: Metaβs Breakthrough in Multilingual Speech Recognition for 1600+ Languages
ποΈ 24 Nov 2025
π AI News & Trends
In an increasingly connected world, speech technology plays a vital role in bridging communication gaps across languages and cultures. Yet, despite rapid progress in Automatic Speech Recognition (ASR), most commercial systems still cater to only a few dozen major languages. Billions of people who speak lesser-known or low-resource languages remain excluded from the benefits of ...
#OmnilingualASR #MultilingualSpeechRecognition #MetaAI #LowResourceLanguages #SpeechTechnology #GlobalCommunication
ποΈ 24 Nov 2025
π AI News & Trends
In an increasingly connected world, speech technology plays a vital role in bridging communication gaps across languages and cultures. Yet, despite rapid progress in Automatic Speech Recognition (ASR), most commercial systems still cater to only a few dozen major languages. Billions of people who speak lesser-known or low-resource languages remain excluded from the benefits of ...
#OmnilingualASR #MultilingualSpeechRecognition #MetaAI #LowResourceLanguages #SpeechTechnology #GlobalCommunication
π€π§ Whisper by OpenAI: The Revolution in Multilingual Speech Recognition
ποΈ 25 Nov 2025
π AI News & Trends
Speech recognition has evolved rapidly over the past decade, transforming the way we interact with technology. From voice assistants to transcription services and real-time translation tools, the ability of machines to understand human speech has redefined accessibility, communication and automation. However, one of the major challenges that persisted for years was achieving robust, multilingual and ...
#Whisper #MultilingualSpeechRecognition #OpenAI #SpeechRecognition #AIAccessibility #VoiceTechnology
ποΈ 25 Nov 2025
π AI News & Trends
Speech recognition has evolved rapidly over the past decade, transforming the way we interact with technology. From voice assistants to transcription services and real-time translation tools, the ability of machines to understand human speech has redefined accessibility, communication and automation. However, one of the major challenges that persisted for years was achieving robust, multilingual and ...
#Whisper #MultilingualSpeechRecognition #OpenAI #SpeechRecognition #AIAccessibility #VoiceTechnology
β€1
π How We Are Testing Our Agents in Dev
π Category: AGENTIC AI
π Date: 2025-12-06 | β±οΈ Read time: 5 min read
Testing that your AI agent is performing as expected is not easy. Here are aβ¦
#DataScience #AI #Python
π Category: AGENTIC AI
π Date: 2025-12-06 | β±οΈ Read time: 5 min read
Testing that your AI agent is performing as expected is not easy. Here are aβ¦
#DataScience #AI #Python
Generating Fake Data in Python!
Instead of spending time coming up with test data β everything can be generated automatically using the
Installing the library:
Importing and configuring:
Generating basic data:
After running, you will get random values for the name, address, description, email, and country.
Generating multiple records:
π₯ Ideal for test filling of databases. A great way to practice working with external libraries and generating data.
πͺ https://t.iss.one/DataScienceM
Instead of spending time coming up with test data β everything can be generated automatically using the
Faker library.Installing the library:
pip install faker
Importing and configuring:
from faker import Faker
# Specify the localization
fake = Faker('ru_RU')
Generating basic data:
print(fake.name())
print(fake.address().replace('\n', ', '))
print(fake.text(max_nb_chars=200))
print(fake.email())
print(fake.country())
After running, you will get random values for the name, address, description, email, and country.
Generating multiple records:
for _ in range(5):
print({
"name": fake.name(),
"email": fake.email(),
"address": fake.address().replace('\n', ', '),
"lat": float(fake.latitude()),
"lon": float(fake.longitude()),
"website": fake.url()
})
Please open Telegram to view this post
VIEW IN TELEGRAM
Telegram
Machine Learning
Machine learning insights, practical tutorials, and clear explanations for beginners and aspiring data scientists. Follow the channel for models, algorithms, coding guides, and real-world ML applications.
Admin: @HusseinSheikho || @Hussein_Sheikho
Admin: @HusseinSheikho || @Hussein_Sheikho
β€4
π How to Climb the Hidden Career Ladder of Data Science
π Category: DATA SCIENCE
π Date: 2025-12-07 | β±οΈ Read time: 14 min read
The behaviors that get you promoted
#DataScience #AI #Python
π Category: DATA SCIENCE
π Date: 2025-12-07 | β±οΈ Read time: 14 min read
The behaviors that get you promoted
#DataScience #AI #Python
β€1
π The Machine Learning βAdvent Calendarβ Day 7: Decision Tree Classifier
π Category: MACHINE LEARNING
π Date: 2025-12-07 | β±οΈ Read time: 8 min read
In Day 6, we saw how a Decision Tree Regressor finds its optimal split byβ¦
#DataScience #AI #Python
π Category: MACHINE LEARNING
π Date: 2025-12-07 | β±οΈ Read time: 8 min read
In Day 6, we saw how a Decision Tree Regressor finds its optimal split byβ¦
#DataScience #AI #Python
β€1
I'm pleased to invite you to join my private Signal group.
All my resources will be free and unrestricted there. My goal is to build a clean community exclusively for smart programmers, and I believe Signal is the most suitable platform for this (Signal is the second most popular app after WhatsApp in the US), making it particularly suitable for us as programmers.
https://signal.group/#CjQKIPcpEqLQow53AG7RHjeVk-4sc1TFxyym3r0gQQzV-OPpEhCPw_-kRmJ8LlC13l0WiEfp
All my resources will be free and unrestricted there. My goal is to build a clean community exclusively for smart programmers, and I believe Signal is the most suitable platform for this (Signal is the second most popular app after WhatsApp in the US), making it particularly suitable for us as programmers.
https://signal.group/#CjQKIPcpEqLQow53AG7RHjeVk-4sc1TFxyym3r0gQQzV-OPpEhCPw_-kRmJ8LlC13l0WiEfp
signal.group
Signal Messenger Group
Follow this link to join a group on Signal Messenger.
β€1
Itβs common to see normalization and standardization used as if they were the same thing, especially because both are often grouped under the generic name βnormalization.β
But they have important differences, and choosing the right one can significantly impact model performance.
Even though both techniques are similar, their goal is the same: reduce scale disparities between variables.
For example, a βsalaryβ feature ranging from 10,000 to 1,000,000 can negatively affect certain algorithms.
Distance-based models like K-means and KNN are highly sensitive to scale.
And in algorithms like Linear Regression and Logistic Regression, large differences in variable scale can mislead the model.
Thatβs why these preprocessing techniques matter so much.
β«οΈ When to Normalize (MinMaxScaler)
Normalization is useful when:
It makes sense for values to be between 0 and 1, or within a specific interval;
Variables have very different ranges and donβt follow a normal distribution;
You're using algorithms that are sensitive to scale, such as distance-based methods.
β«οΈ When to Standardize (StandardScaler)
Standardization is ideal when:
The data has no natural bounds and doesnβt need to be between 0 and 1;
You want zero mean and unit variance;
Variables follow (or approximate) a normal distribution;
You use models like Linear Regression, Logistic Regression or PCA.
In short
Standardization: centers the data around mean 0 and std 1, preserving distribution shape.
Normalization: rescales values into a specific interval (usually 0β1), changing the scale without preserving the original distribution.
https://t.iss.one/DataScienceM
But they have important differences, and choosing the right one can significantly impact model performance.
Even though both techniques are similar, their goal is the same: reduce scale disparities between variables.
For example, a βsalaryβ feature ranging from 10,000 to 1,000,000 can negatively affect certain algorithms.
Distance-based models like K-means and KNN are highly sensitive to scale.
And in algorithms like Linear Regression and Logistic Regression, large differences in variable scale can mislead the model.
Thatβs why these preprocessing techniques matter so much.
β«οΈ When to Normalize (MinMaxScaler)
Normalization is useful when:
It makes sense for values to be between 0 and 1, or within a specific interval;
Variables have very different ranges and donβt follow a normal distribution;
You're using algorithms that are sensitive to scale, such as distance-based methods.
β«οΈ When to Standardize (StandardScaler)
Standardization is ideal when:
The data has no natural bounds and doesnβt need to be between 0 and 1;
You want zero mean and unit variance;
Variables follow (or approximate) a normal distribution;
You use models like Linear Regression, Logistic Regression or PCA.
In short
Standardization: centers the data around mean 0 and std 1, preserving distribution shape.
Normalization: rescales values into a specific interval (usually 0β1), changing the scale without preserving the original distribution.
https://t.iss.one/DataScienceM
β€4π1π₯1
π Artificial Intelligence, Machine Learning, Deep Learning, and Generative AI β Clearly Explained
π Category: ARTIFICIAL INTELLIGENCE
π Date: 2025-12-07 | β±οΈ Read time: 12 min read
Understanding AI in 2026 β from machine learning to generative models
#DataScience #AI #Python
π Category: ARTIFICIAL INTELLIGENCE
π Date: 2025-12-07 | β±οΈ Read time: 12 min read
Understanding AI in 2026 β from machine learning to generative models
#DataScience #AI #Python
β€2π1
π Master Data Science & Programming!
Unlock your potential with this curated list of Telegram channels. Whether you need books, datasets, interview prep, or project ideas, we have the perfect resource for you. Join the community today!
π° Machine Learning with Python
Learn Machine Learning with hands-on Python tutorials, real-world code examples, and clear explanations for researchers and developers.
https://t.iss.one/CodeProgrammer
π Machine Learning
Machine learning insights, practical tutorials, and clear explanations for beginners and aspiring data scientists. Follow the channel for models, algorithms, coding guides, and real-world ML applications.
https://t.iss.one/DataScienceM
π§ Code With Python
This channel delivers clear, practical content for developers, covering Python, Django, Data Structures, Algorithms, and DSA β perfect for learning, coding, and mastering key programming skills.
https://t.iss.one/DataScience4
π― PyData Careers | Quiz
Python Data Science jobs, interview tips, and career insights for aspiring professionals.
https://t.iss.one/DataScienceQ
πΎ Kaggle Data Hub
Your go-to hub for Kaggle datasets β explore, analyze, and leverage data for Machine Learning and Data Science projects.
https://t.iss.one/datasets1
π§βπ Udemy Coupons | Courses
The first channel in Telegram that offers free Udemy coupons
https://t.iss.one/DataScienceC
π ML Research Hub
Advancing research in Machine Learning β practical insights, tools, and techniques for researchers.
https://t.iss.one/DataScienceT
π¬ Data Science Chat
An active community group for discussing data challenges and networking with peers.
https://t.iss.one/DataScience9
π Python Arab| Ψ¨Ψ§ΩΨ«ΩΩ ΨΉΨ±Ψ¨Ω
The largest Arabic-speaking group for Python developers to share knowledge and help.
https://t.iss.one/PythonArab
π Data Science Jupyter Notebooks
Explore the world of Data Science through Jupyter Notebooksβinsights, tutorials, and tools to boost your data journey. Code, analyze, and visualize smarter with every post.
https://t.iss.one/DataScienceN
πΊ Free Online Courses | Videos
Free online courses covering data science, machine learning, analytics, programming, and essential skills for learners.
https://t.iss.one/DataScienceV
π Data Analytics
Dive into the world of Data Analytics β uncover insights, explore trends, and master data-driven decision making.
https://t.iss.one/DataAnalyticsX
π§ Learn Python Hub
Master Python with step-by-step courses β from basics to advanced projects and practical applications.
https://t.iss.one/Python53
βοΈ Research Papers
Professional Academic Writing & Simulation Services
https://t.iss.one/DataScienceY
ββββββββββββββββββ
Admin: @HusseinSheikho
Unlock your potential with this curated list of Telegram channels. Whether you need books, datasets, interview prep, or project ideas, we have the perfect resource for you. Join the community today!
Learn Machine Learning with hands-on Python tutorials, real-world code examples, and clear explanations for researchers and developers.
https://t.iss.one/CodeProgrammer
Machine learning insights, practical tutorials, and clear explanations for beginners and aspiring data scientists. Follow the channel for models, algorithms, coding guides, and real-world ML applications.
https://t.iss.one/DataScienceM
This channel delivers clear, practical content for developers, covering Python, Django, Data Structures, Algorithms, and DSA β perfect for learning, coding, and mastering key programming skills.
https://t.iss.one/DataScience4
Python Data Science jobs, interview tips, and career insights for aspiring professionals.
https://t.iss.one/DataScienceQ
Your go-to hub for Kaggle datasets β explore, analyze, and leverage data for Machine Learning and Data Science projects.
https://t.iss.one/datasets1
The first channel in Telegram that offers free Udemy coupons
https://t.iss.one/DataScienceC
Advancing research in Machine Learning β practical insights, tools, and techniques for researchers.
https://t.iss.one/DataScienceT
An active community group for discussing data challenges and networking with peers.
https://t.iss.one/DataScience9
The largest Arabic-speaking group for Python developers to share knowledge and help.
https://t.iss.one/PythonArab
Explore the world of Data Science through Jupyter Notebooksβinsights, tutorials, and tools to boost your data journey. Code, analyze, and visualize smarter with every post.
https://t.iss.one/DataScienceN
Free online courses covering data science, machine learning, analytics, programming, and essential skills for learners.
https://t.iss.one/DataScienceV
Dive into the world of Data Analytics β uncover insights, explore trends, and master data-driven decision making.
https://t.iss.one/DataAnalyticsX
Master Python with step-by-step courses β from basics to advanced projects and practical applications.
https://t.iss.one/Python53
Professional Academic Writing & Simulation Services
https://t.iss.one/DataScienceY
ββββββββββββββββββ
Admin: @HusseinSheikho
Please open Telegram to view this post
VIEW IN TELEGRAM
β€1
π The Machine Learning βAdvent Calendarβ Day 8: Isolation Forest in Excel
π Category: MACHINE LEARNING
π Date: 2025-12-08 | β±οΈ Read time: 11 min read
Isolation Forest may look technical, but its idea is simple: isolate points using random splits.β¦
#DataScience #AI #Python
π Category: MACHINE LEARNING
π Date: 2025-12-08 | β±οΈ Read time: 11 min read
Isolation Forest may look technical, but its idea is simple: isolate points using random splits.β¦
#DataScience #AI #Python
β€3
π€π§ Distil-Whisper: Faster, Smaller, and Smarter Speech Recognition by Hugging Face
ποΈ 08 Dec 2025
π AI News & Trends
The evolution of Automatic Speech Recognition (ASR) has reshaped how humans interact with technology. From dictation tools and live transcription to smart assistants and media captioning, ASR technology continues to bridge the gap between speech and digital communication. However, achieving real-time, high-accuracy transcription often comes at the cost of heavy computational requirements until now. Enter ...
#DistilWhisper #FasterSpeechRecognition #SmallerModels #HuggingFace #ASRTechnology #RealTimeTranscription
ποΈ 08 Dec 2025
π AI News & Trends
The evolution of Automatic Speech Recognition (ASR) has reshaped how humans interact with technology. From dictation tools and live transcription to smart assistants and media captioning, ASR technology continues to bridge the gap between speech and digital communication. However, achieving real-time, high-accuracy transcription often comes at the cost of heavy computational requirements until now. Enter ...
#DistilWhisper #FasterSpeechRecognition #SmallerModels #HuggingFace #ASRTechnology #RealTimeTranscription
π The AI Bubble Will PopβββAnd Why That Doesnβt Matter
π Category: ARTIFICIAL INTELLIGENCE
π Date: 2025-12-08 | β±οΈ Read time: 7 min read
How historyβs biggest tech bubble explains where AI is headed next
#DataScience #AI #Python
π Category: ARTIFICIAL INTELLIGENCE
π Date: 2025-12-08 | β±οΈ Read time: 7 min read
How historyβs biggest tech bubble explains where AI is headed next
#DataScience #AI #Python
π How to Create an ML-Focused Newsletter
π Category: LLM APPLICATIONS
π Date: 2025-12-08 | β±οΈ Read time: 7 min read
Learn how to make a newsletter with AI tools
#DataScience #AI #Python
π Category: LLM APPLICATIONS
π Date: 2025-12-08 | β±οΈ Read time: 7 min read
Learn how to make a newsletter with AI tools
#DataScience #AI #Python
β€1
π Optimizing PyTorch Model Inference on CPU
π Category: DEEP LEARNING
π Date: 2025-12-08 | β±οΈ Read time: 20 min read
Flyinβ Like a Lion on Intel Xeon
#DataScience #AI #Python
π Category: DEEP LEARNING
π Date: 2025-12-08 | β±οΈ Read time: 20 min read
Flyinβ Like a Lion on Intel Xeon
#DataScience #AI #Python
β€3
π Personal, Agentic Assistants: A Practical Blueprint for a Secure, Multi-User, Self-Hosted Chatbot
π Category: AGENTIC AI
π Date: 2025-12-09 | β±οΈ Read time: 10 min read
Build a self-hosted, end-to-end platform that gives each user a personal, agentic chatbot that canβ¦
#DataScience #AI #Python
π Category: AGENTIC AI
π Date: 2025-12-09 | β±οΈ Read time: 10 min read
Build a self-hosted, end-to-end platform that gives each user a personal, agentic chatbot that canβ¦
#DataScience #AI #Python
β€4