👋 Welcome to AI-ML..new-to-know

Are you new to the world of Artificial Intelligence and Machine Learning?

Do you want to know how real-world models and algorithms work under the hood?

This repository is built just for you — a hands-on journey to go from being new to knowing key concepts in AI and ML. Through practical examples, annotated notebooks, and real-world datasets, you'll explore fundamental techniques, modern frameworks, and advanced architectures using Python.

Whether you're a beginner, student, or curious practitioner, AI-ML..new-to-know will guide your path from learning the basics to applying what you know with confidence.

---

🧠 Contents

Data Science Essentials

Notebook / Resource	Topics Covered
0. Intro to Data Analysis in Python	Overview of data analysis using Python
1. NumPy Basics - Arrays and Vectorized operations	NumPy arrays, broadcasting, ufuncs
2. Getting Started with Pandas	Series, DataFrames, indexing
3. Data Loading, Storage and File Formats	Reading/writing CSV, Excel, JSON
4. Data Cleaning and Preparation	Handling missing values, duplicates, text parsing
5. Data Wrangling - Join, Combine and Reshape	Merging, concatenating, reshaping data
6. Plotting and Visualization	Matplotlib, seaborn, plotting with pandas
7. Data Aggregation and Group Operations	groupby(), aggregation, pivot tables
8. Time Series	Date/time handling, resampling, rolling windows
9. Advanced pandas	MultiIndexing, reshaping, categorical data
10. Data Analysis Examples	Real-world data manipulation case studies
Data Science Interview Series✔️✅-1.pdf	Common interview questions and concepts

📁 ML Notebooks

Notebook / Resource	Topics Covered
ML0_Time Series Analysis	Trend, seasonality, decomposition
ML1_Linear Models	Linear & Logistic Regression
ML1_Regression_Analysis	Residuals, model evaluation
ML2_Support Vector Machines	SVM theory and kernel tricks
ML3_K_means_Clustering	Clustering techniques
ML4_Decision_Trees	ID3, Gini, pruning
ML5_Association_Rule_Mining	Apriori, support/confidence
ML6_Monte_Carlo_Methods	Simulation-based methods
ML7_Reinforcement_Learning	Q-learning, reward maximization
ML8_Dimensionality_Reduction_Techniques	PCA, SVD, t-SNE, LDA

📁 Neural Networks & Deep Learning

Notebook / Resource	Topics Covered
NN0_PyTorch_Fundamentals	Tensors, autograd, models
NN1_DL_Basics	Perceptrons, activation functions
NN2_Neural_Networks_code_practice	Implementation of MLPs
NN3_Optimization_Techniques	Gradient descent variants, Adam
NN4_CNN	Convolutional layers, pooling, image classification
NN5_RNN	RNN, LSTM, BiLSTM, GRU
NN6_Not_AI	Transformer, GenAI, GAN, VAE
NN7_Autoencoders	Encoder, Decoder, Types of autoencoders, VAE
NN8_Diffusion_Models	DDPMs
NN9_AutoML	HPO, NAS, Meta Learning, Auto-Sklearn
NN10_Graph_Network_Analysis	Graph Basics, Graph analysis, GNN basics

📁 OpenCV

• Open Source Computer Vision Library
• A comprehensive personal repository of OpenCV projects
  1. Image Transformations
  2. Edge Detection Techniques
  3. Feature detection and matching
  4. Face and eye detection
  5. Object detection and tracking
  6. Background removal techniques
  7. Texture Analysis and Synthesis

---

📜 License & Usage

This repository is intended purely for educational purposes to help learners explore AI and ML concepts through practical examples and hands-on notebooks.

⚠️ Note: Many of the contents, images, and resources used here are sourced or adapted from publicly available educational materials, courses, blogs, and books. While efforts have been made to provide attribution, some references may be incomplete or unintentionally omitted. If you identify any such case, feel free to raise an issue or pull request for correction.

Feel free to modify the code, run experiments, and explore various techniques and applications.

---

📬 Contact

Mailapalli Purushotham

📧 purus15987@gmail.com

🔗 GitHub: https://github.com/purus15987

🔗 LinkedIn: https://www.linkedin.com/in/purus15987/