Day 11/∞ of my AI/ML journey
Taking a short break from studying today.
Quick question for the community:
Which concept in Machine Learning or Deep Learning took you the longest to truly understand?
Curious to hear your experiences.
#DeepLearning#AI
Hey @X algorithm 👋
I'm looking to #connect with people interested in:
Frontend & Backend
App Development
DevOps
Data Science
LeetCode & DSA
Freelancing
Building in public
If that's you, let's connect 🤝
Day 10/∞ of my AI/ML journey
Today was a consolidation day.
✅ Revised Machine Learning fundamentals
✅ Improved my Kaggle profile
✅ Joined my first Kaggle competition: Titanic - Machine Learning from Disaster
Time to put theory into practice.
🔗 https://t.co/yijM6slMCq
Day 9/∞ of my AI/ML journey
Started learning Convolutional Neural Networks (CNNs).
Today's focus:
• Why CNNs outperform ANNs for images
• Convolutions & Feature Maps
• Pooling Layers
• CNN architectures
• Built my first CNN with TensorFlow/Keras
#DeepLearning#AI
Day 6/∞ of ML
Today I explored how ML learns without labeled data.
✔ Ensemble Learning
✔ K-Means Clustering
✔ PCA
✔ DBSCAN
Learning how to discover hidden patterns, reduce dimensions, and build stronger models through ensemble methods.
#MachineLearning#DataScience#AI
Day 8/∞ of AI/ML journey
Started my Deep Learning journey by exploring:
• Perceptrons
• Artificial Neural Networks (ANN)
• Activation Functions
• Log Loss
• Optimisers
Understanding how these components work together made neural networks feel much less like a black box.
Day 7/∞ of my ML journey
Wrapped up the fundamentals of Machine Learning.
Over the past week, I explored supervised & unsupervised learning, ensemble methods, dimensionality reduction, and built ML projects.
Tomorrow, I begin Deep Learning.
Onward! 🧠
Day 5/∞ of my ML journey
Built and deployed a Heart Disease Prediction app using Machine Learning.
✅ Data preprocessing
✅ Model training
✅ Prediction interface
✅ Live deployment
💻 https://t.co/0oXn0WomLq
🌐 https://t.co/cMJEHEE4GQ
#MachineLearning#BuildInPublic
Day 4/∞ of my AI/ML journey
Today I explored some of the core supervised learning algorithms:
• Logistic Regression
• KNN
• Decision Trees
• Random Forest
• SVM
• Naive Bayes
Each algorithm has its strengths—the key is knowing when to use which one.
#MachineLearning#AI
Day 3/∞ of ML
Today's project: Insurance Cost Prediction using Linear Regression.
Applied the complete ML workflow—from preprocessing and feature engineering to training and evaluating the model.
Repo 🔗
https://t.co/XDBtI8oT7u
#BuildInPublic#MachineLearning