Before neural networks, there was regression.
Before ChatGPT, there was least squares.
Understanding Linear Regression means understanding how machines learn relationships — the DNA of all supervised learning.
#AI #DataScience #MLZoomcamp
Before neural networks, there was regression.
Before ChatGPT, there was least squares.
Understanding Linear Regression means understanding how machines learn relationships — the DNA of all supervised learning.
#AI #DataScience #MLZoomcamp
This module was about getting into ML with Linear Regression — from understanding the fundamentals to building and evaluating a regression model.
Link: colab.research.google.com/drive/11QI2t...
#mlzoomcamp @Alexey Grigorev
This module was about getting into ML with Linear Regression — from understanding the fundamentals to building and evaluating a regression model.
Link: colab.research.google.com/drive/11QI2t...
#mlzoomcamp @Alexey Grigorev
It’s math + data + pattern-finding at scale.
📌 If you can define a task with inputs & desired outputs, there’s a chance you can teach a machine to learn it.
Just started #MLZoomcamp and I’m already rethinking what “learning” really means 🤖
#LearningInPublic
It’s math + data + pattern-finding at scale.
📌 If you can define a task with inputs & desired outputs, there’s a chance you can teach a machine to learn it.
Just started #MLZoomcamp and I’m already rethinking what “learning” really means 🤖
#LearningInPublic
These 2 weeks were about 1. Introduction to ML:
- Difference between ML and rule-based systems
- What supervised ML is
- CRISP-DM
- The model selection step
- Setting up the environment
➡️Next step: 2. ML for Regression
#mlzoomcamp
These 2 weeks were about 1. Introduction to ML:
- Difference between ML and rule-based systems
- What supervised ML is
- CRISP-DM
- The model selection step
- Setting up the environment
➡️Next step: 2. ML for Regression
#mlzoomcamp
Linear regression assumes linearity, independence, homoscedasticity, and normality — the same assumptions engineers rely on when modeling heat transfer, vibration, or current flow.
It’s not just statsnbut it’s physics written in matrix form.
#Engineering #DataScience #MLZoomcamp
Linear regression assumes linearity, independence, homoscedasticity, and normality — the same assumptions engineers rely on when modeling heat transfer, vibration, or current flow.
It’s not just statsnbut it’s physics written in matrix form.
#Engineering #DataScience #MLZoomcamp
✨ Takeaway: ML is a lifecycle—business & data prep matter most.
🤔 Best part: Shifting from coding rules to letting data find them via vectorization!
➡️ Next: Regression!
#mlzoomcamp @alexeygrigorev.bsky.social
✨ Takeaway: ML is a lifecycle—business & data prep matter most.
🤔 Best part: Shifting from coding rules to letting data find them via vectorization!
➡️ Next: Regression!
#mlzoomcamp @alexeygrigorev.bsky.social
Learned about
🔹 Decision Trees for regression
🔹 Random Forest
🔹 Feature importance
🔹 XGBoost parameter tuning
✨More trees isn't always better. There's a sweet spot for model complexity vs performance
➡️ Next up: Midterm project
@Al_Grigor #DataTalkClub
Learned about
🔹 Decision Trees for regression
🔹 Random Forest
🔹 Feature importance
🔹 XGBoost parameter tuning
✨More trees isn't always better. There's a sweet spot for model complexity vs performance
➡️ Next up: Midterm project
@Al_Grigor #DataTalkClub
It measures a model's ability to separate positive and negative classes, independent of any specific threshold.
🎯 1.0 = Perfect classifier 🤷 0.5 = Random guessing
#MLZoomcamp #DataTalksClub #LearningInPublic
It measures a model's ability to separate positive and negative classes, independent of any specific threshold.
🎯 1.0 = Perfect classifier 🤷 0.5 = Random guessing
#MLZoomcamp #DataTalksClub #LearningInPublic
github.com/RuiFSP/mlzoo...
#MachineLearning #DeepLearning #FootballPrediction #DataScience #ML #DataScience #SportsAnalytics #PremierLeague #DataTalksClub
github.com/RuiFSP/mlzoo...
#MachineLearning #DeepLearning #FootballPrediction #DataScience #ML #DataScience #SportsAnalytics #PremierLeague #DataTalksClub
A linear model scores a customer, then the sigmoid function squashes that score into a 0-1 probability. High probability = high churn risk! 🎯
Learn more from Alexey Grigorev!
#MLZoomcamp #DataTalksClub #MachineLearning
A linear model scores a customer, then the sigmoid function squashes that score into a 0-1 probability. High probability = high churn risk! 🎯
Learn more from Alexey Grigorev!
#MLZoomcamp #DataTalksClub #MachineLearning
Most ML projects don’t fail because of bad models.
They fail because we skip CRISP-DM:
Business understanding
Data understanding
Data prep
Modeling
Evaluation
Deployment
A 90s framework still relevant today.
It’s not fancy. But it works.
#CRISPDM #MLZoomcamp #LearningInPublic
Most ML projects don’t fail because of bad models.
They fail because we skip CRISP-DM:
Business understanding
Data understanding
Data prep
Modeling
Evaluation
Deployment
A 90s framework still relevant today.
It’s not fancy. But it works.
#CRISPDM #MLZoomcamp #LearningInPublic