Welcome to my 100 Days of AI & Machine Learning learning journey! This repository documents my progress as I explore various topics in AI and ML through tutorials and resources from Krish Naik, CampusX, and PW Skills.
This repo serves as a log of the concepts I've learned, the projects I've worked on, and the practical applications I’ve implemented. Each folder contains theory notes that I’ve clicked and posted during this learning journey. The journey spans across many foundational and advanced topics, including Data Preprocessing, Machine Learning, Deep Learning, Natural Language Processing (NLP), and Large Language Models (LLMs).
Here’s a summary of the topics I’ve covered so far:
- Day 1: Pandas overview and basic dataset manipulations
- Day 2: Numpy functions and operations
- Day 3: Upscaling and downscaling
- Day 4: SMOTE for imbalanced datasets
- Day 5: Feature scaling (Unit Vector)
- Day 6: Feature extraction (Covariance and Correlation)
- Day 7: Exploratory Data Analysis (Algerian Dataset)
- Day 8 - Day 9: Linear Regression and Logistic Regression (Multiclass)
- Day 10: Decision Trees (Theory and Model Implementation)
- Day 11: Support Vector Machine (SVM) Kernels and Theory
- Day 12: Naive Bayes (Theory + Practical)
- Day 13: Random Forest (Theory and Implementation)
- Day 14: Boosting - XGBoost (Theory)
- Day 15: K-Nearest Neighbors (KNN) (Theory)
- Day 16: Principal Component Analysis (PCA) (Mathematics and Geometry)
- Day 17: Clustering (DBSCAN Practical)
- Day 18: Time Series Analysis
- Day 19: Deep Learning - Perceptron
- Day 20: Activation Function and Backpropagation
- Day 26 - Day 33: Krish Naik’s Live Deep Learning Playlist (ANN, CNN, and more)
- Day 34: Introduction to NLP
- Day 35: Stemming, Lemmatization, and NLP basics
- Day 36 - Day 39: Word Embeddings, RNN, LSTM, and Bidirectional LSTM
- Day 40: History of Large Language Models (LLMs)
- Day 41: History of LLMs
- Day 42 - Day 44: Attention Mechanisms and Self-Attention
- Day 45: Beginner's Guide to Transformers (Hugging Face Testing)
- Statistics: p-value, Z-test, T-test, Chi-Square, F-test, and ANOVA
- Deep Learning Theory and Projects: Practical codes and CNN optimization using Keras Tuner.
- Fake News Classifier using LSTM: A real-world project that classifies news articles as real or fake using LSTM networks.
This journey is still in progress. I'm currently delving deeper into Deep Learning and NLP, and more updates will be added as I explore advanced concepts like Transformers, BERT, and large-scale model tuning.
Stay tuned for more!
This learning journey has been guided by content from:
- LinkedIn: [Chandraparsad]