TGViewer
Channel Public Channel
Data science/ML/AI

Data science/ML/AI

@datascience_bds

Data science and machine learning hub

Python, SQL, stats, ML, deep learning, projects, PDFs, roadmaps and AI resources.

For beginners, data scientists and ML engineers
πŸ‘‰ https://rebrand.ly/bigdatachannels

DMCA: @disclosure_bds
Contact: @mldatascientist
Subscribers
14.1K
Photos
611
Videos
7
Links
341

Showing posts older than #998 Β· Back to latest

Older Posts 17 shown
Post #996 1.93K

Forwarded from Cool GitHub repositories

lerobot

This is an end-to-end library for robot learning. It handles the entire pipeline from loading and processing robotics datasets to training policies and deploying them in simulation or on real hardware.

Creator:   huggingface
Stars ⭐️:  19,000
Forked by: 3,000

Github Repo:
https://github.com/huggingface/lerobot

#robotics #AI
βž–βž–βž–βž–βž–βž–βž–βž–βž–βž–βž–βž–βž–βž–    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group
GitHub GitHub - huggingface/lerobot: πŸ€— LeRobot: Making AI for Robotics more accessible with end-to-end learning πŸ€— LeRobot: Making AI for Robotics more accessible with end-to-end learning - huggingface/lerobot
  • ❀ 3
Post #995 1.6K
Top Data Science Tools By Function
  • ❀ 3
  • πŸ‘ 1
Post #992 1.84K
Top 6 Types of AI Models
  • ❀ 4
Post #990 1.82K
Skills Needed To Become Data Analyst
  • ❀ 5
Post #988 1.74K
Regularization: The Art of Keeping Models Humble

Overfitting is the β€œego problem” of models. They memorize training data and forget how to generalize.
Regularization is how we humble them.

➑️ L1 (Lasso): Shrinks some weights to zero β†’ performs feature selection.
➑️ L2 (Ridge): Reduces all weights slightly β†’ smooths learning.
➑️ Dropout: Randomly removes neurons during training β†’ prevents co-dependence.

It’s not about punishment but it’s about discipline.
Regularization teaches models to focus on patterns, not exceptions.

πŸ’­ Remember: The best models don’t just fit data. They respect uncertainty.
  • ❀ 9
  • 😁 1
Post #986 1.75K
List of AI Project Ideas πŸ‘¨πŸ»β€πŸ’»

Beginner Projects

πŸ”Ή Sentiment Analyzer
πŸ”Ή Image Classifier
πŸ”Ή Spam Detection System
πŸ”Ή Face Detection
πŸ”Ή Chatbot (Rule-based)
πŸ”Ή Movie Recommendation System
πŸ”Ή Handwritten Digit Recognition
πŸ”Ή Speech-to-Text Converter
πŸ”Ή AI-Powered Calculator
πŸ”Ή AI Hangman Game

Intermediate Projects

πŸ”Έ AI Virtual Assistant
πŸ”Έ Fake News Detector
πŸ”Έ Music Genre Classification
πŸ”Έ AI Resume Screener
πŸ”Έ Style Transfer App
πŸ”Έ Real-Time Object Detection
πŸ”Έ Chatbot with Memory
πŸ”Έ Autocorrect Tool
πŸ”Έ Face Recognition Attendance System
πŸ”Έ AI Sudoku Solver

Advanced Projects

πŸ”Ί AI Stock Predictor
πŸ”Ί AI Writer (GPT-based)
πŸ”Ί AI-powered Resume Builder
πŸ”Ί Deepfake Generator
πŸ”Ί AI Lawyer Assistant
πŸ”Ί AI-Powered Medical Diagnosis
πŸ”Ί AI-based Game Bot
πŸ”Ί Custom Voice Cloning
πŸ”Ί Multi-modal AI App
πŸ”Ί AI Research Paper Summarizer
  • ❀ 9
  • πŸ‘ 1
Post #985 1.65K
🚨 When & How Jupyter Notebooks Fail (And What To Use Instead)

Hey Data Folks! πŸ‘©β€πŸ’»πŸ‘¨β€πŸ’»
Let’s talk about Jupyter Notebooks β€” powerful for exploration, but risky in production. Here’s why:

❌ Problems with Notebooks:
1. Out-of-order execution β†’ hidden bugs.
2. Code changes after execution β†’ inconsistent results.
3. Data leakage β†’ sensitive info in outputs.
4. Security risks β†’ tokens/keys exposed.
5. Hard to apply engineering practices β†’ no modular code, testing, CI/CD.
6. Collaboration pain β†’ merge conflicts, JSON issues.
7. Reproducibility issues β†’ missing dependencies, versions.

βœ… When They’re Useful:
- Quick data exploration & prototyping.
- Knowledge sharing (clean, runnable from top to bottom).
- Teaching / hands-on tutorials (with solution notebooks).

πŸ”§ What to Use Instead:
- For production code β†’ .py files + IDEs.
- For workflows β†’ template repos & reproducible setups.
- For deployment β†’ MLOps tools, pipelines, automation.

πŸ’‘ Key Takeaways:
- Use notebooks for exploration & teaching.
- Use structured code + pipelines for production & deployment.
- Always document dependencies, keep notebooks clean, never commit secrets!
  • ❀ 6
  • πŸ‘ 2
Post #980 1.71K
Pandas Cheatsheet For Data Analysis
  • ❀ 4
Post #978 2.1K
Hey everyone πŸ‘‹

Some time ago, I asked if I should start a Data Science educational series and since 96% of you said yes, I began creating it.

But many of you also asked for real, hands-on experience with projects, not just lessons. So I decided to shift gears. It’s now becoming a full practical coding course! πŸ’»

My goal is to help you build skills that get you job-ready, not just teach theory. It’s taking a bit longer, but I promise it’ll be worth it.

Thank you all for your support and patience ❀️
I’ll let you know as soon as we’re ready to start!
  • ❀ 21
  • πŸ‘ 3
  • πŸ₯° 2
Older posts β†’
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook β†’Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 β†’