Top Tweets for #100daysofMachineLearning
Day 16 of #30dayscoding named #GandFadCoding
- complete 5 topics of python @Hiteshdotcom and @piyushgarg_dev
- also learning #100DaysofMachineLearning by CampusX watched day 15 video
This was Day 16 of my #GandFadCoding
#100DaysOfMachineLearning Day 3 Got to know about logistic regression

#100DaysOfMachineLearning Day 2 Got to know about tensors.

#100DaysOfMachineLearning Machine Learning Day 1 on https://t.co/Zqotga7FH4

Learning ML alone is hard.
Learning ML together is fun π
Iβm looking for people to collaborate on ML projects as part of #100DaysOfMachineLearning.
If youβre building, learning, or just curious β letβs connect π€
Comment βMLβ or DM me.
#MLTwitter #DataScienceCommunity #AI
π§ Offline vs Online Machine Learning β in 1 minute
Offline ML = Train once on past data
Online ML = Learn continuously from live data
Same goal. Very different approach.
Part of my #100DaysOfMachineLearning π
π Details in comments
#MachineLearning #AI #DataScience #LearnIn

Day 17 of #100DaysOfMachineLearning
Today I learned about optimizers.
Gradient descent tells a model where to go.
Optimizers decide how fast and how smoothly it gets there.
Momentum, RMSProp, Adam, AdamW
All built to make learning faster and more stable.
Free to read π
https://t.co/uSgepJy5x0
#MachineLearning #DataScience #AI #DeepLearning #MLForBeginners

Day 16 of #100DaysOfMachineLearning
Todayβs topic: Gradient Descent
This is how machines actually learn:
make a prediction β measure the error β move parameters slightly β repeat.
The learning rate decides how big each step is.
Too small and training is slow.
Too big and training breaks.
π Free to read:
https://t.co/dPtUlmwMnb
#MachineLearning #AI #DataScience #DeepLearning #MLForBeginners #GradientDescent #TechLearning
Day 12 of #100DaysOfMachineLearning
Today I learned about Overfitting and Underfitting β two problems that can make or break a model.
Underfitting happens when the model learns too little.
Overfitting happens when it learns too much.
The real goal is balance: a model that generalizes well on new data.
π Free to read:
https://t.co/OE714MkFh3
#MachineLearning #DataScience #AI #DeepLearning #TechLearning #MLForBeginners

Day 11 of #100DaysOfMachineLearning
Today I covered one of the most important steps in ML:
Data Preprocessing and Feature Engineering.
Clean data matters more than complex models.
Handling missing values, encoding categories, scaling features, and engineering new ones can transform your results.
π Full article (free):
https://t.co/KBHEzubOgW
#MachineLearning #DataScience #AI #MLForBeginners #FeatureEngineering #DataPreprocessing #DeepLearning #AIExplained #TechLearning

Day 9 of #100DaysOfMachineLearning π§
Todayβs topic: Classification β how AI learns to make decisions, not just predictions.
From spam filters to fraud detection to facial recognition β classification helps machines separate data into categories based on patterns.
π Free to read:
π https://t.co/XQ5oFcOiV2
#MachineLearning #AI #DataScience #DeepLearning #AIExplained #MLForBeginners #AITrends2025 #AICommunity #Classification #TechLearning

Day 74:
β
Explored the foundation of gradient-free learning in Tangled Program Graphs
β
60-minute walk and danceππ»π
#100DaysofMachineLearning #AI

Day 30 of #100DaysOfMachineLearning
I completed Exploratory Data Analysis. It included
-> EDA in python
-> Advance EDA
->Time Series Data Visualization.
Off to Model Evaluation next..

Finished my MERN full-stack journey and ready for the next big leap π Starting #100DaysOfMachineLearning with @CampusX π€
From building websites to building smart systemsβ¦ letβs see where this takes me! π
Whoβs learning ML too? Letβs connect!
#AI #ML #CampusX #LearningTogether

Week 3 of my #100DaysOfMachineLearning has been intense!
From Day 15 to Day 22, these are some topics that I did:
1. Explored Simple Linear Regression β understanding how one feature can predict an outcome.
2. Moved to Multiple Linear Regression β where things get more real.

Day 14 of #100DaysOfMachineLearning
Completed these within the last few days-
1. Complete case analysis
2. Arbitrary value imputation
3. Missing categorical value
4. Automatically select imputer parameters
5. KNN Imputer
6. Outlier removal using Z Score

Day 13 of #100DaysOfMachineLearning
Hereβs what I coded in the past few days:
1. Handling missing categorical data
2. Doing a complete case analysis (basically dropping rows with missing values)
3.Trying out arbitrary value imputation

Day 12 of #100DaysOfMachineLearning
I did these topics within the last 3 days:
1. From Statistics, I did- probability distribution function (pdf, pmf, cdf) and Normal distribution.
2. I did 6 cases of handling missing data using:

Day 11 of #100DaysOfMachineLearning
I started diving into maths for machine learning. I've always heard that Statistics is a non-negotiable for machine learning.
Although was never particularly a very big fan of this subject, but I did these topics under Descriptive Statistics

Day 10 of #100DaysOfMachineLearning
So, I coded the stuff learnt the previous day( column Transformer, sklearn Pipelines, function transformer, power transformer).
I started the theory of machine learning from geeksforgeeks too. I really like this site for concept clarity.

Trends for you
Most Popular Users

Elon Musk 
@elonmusk
240.1M followers

Barack Obama 
@barackobama
119.3M followers

Donald J. Trump 
@realdonaldtrump
111.6M followers

Cristiano Ronaldo 
@cristiano
108.9M followers

Narendra Modi 
@narendramodi
107M followers

Rihanna 
@rihanna
97.3M followers

NASA 
@nasa
92.1M followers

Justin Bieber 
@justinbieber
90.6M followers

KATY PERRY 
@katyperry
86.8M followers

Taylor Swift 
@taylorswift13
80.6M followers

Lady Gaga 
@ladygaga
72.1M followers

Kim Kardashian 
@kimkardashian
69.4M followers

YouTube 
@youtube
68.6M followers

Virat Kohli 
@imvkohli
68.5M followers

Bill Gates 
@billgates
63.4M followers

The Ellen Show
@theellenshow
62.5M followers

CNN 
@cnn
61.9M followers

Neymar Jr 
@neymarjr
61M followers

X 
@x
60.9M followers

CNN Breaking News 
@cnnbrk
59.9M followers




















