How saransh-basu-01/ai_engineering works
This repository is a self-guided AI-engineering learning workspace, not a single runtime application. A learner explores topic notebooks and exercises, then runs from-scratch implementations and observes worked examples or experiment output. The tree and sampled Python sources support mathematical foundations, probability and inference, dimensionality reduction, and autodifferentiation/optimization; broader README capabilities such as data-processing pipelines are not represented by a dedicated subsystem in the supplied tree. Notebook internals were not sampled, so their wiring is not inferred.
Main entry points: probability.py Probability code · Bayes.py Bayes and classifier · information_entropy.py Entropy code · Autograd.py Autograd and MLP
Components 18
Math foundations
- Linear algebra
Math_Fundamentals/Linear_Algebra_intution - Vector operations
Math_Fundamentals/Vector_matrices_and_operations - Matrix transforms
Math_Fundamentals/Matrix_Transformations and EigenValues - Derivatives
Math_Fundamentals/Derivatives_and_Gradients
Probability and inference
- Information theory
Math_Fundamentals/Information_theory - Probability distributions
Math_Fundamentals/Probability_Distributions - Bayes rule
Math_Fundamentals/Bayes_Rule - Probability code
Math_Fundamentals/Probability_Distributions/probability.py - Bayes and classifier
Math_Fundamentals/Bayes_Rule/Bayes.py - Entropy code
Math_Fundamentals/Information_theory/information_entropy.py
Learning mechanics
- Automatic differentiation
Math_Fundamentals/Chain_Rule_And_Automatic_Differentiation - Autograd and MLP
Math_Fundamentals/Chain_Rule_And_Automatic_Differentiation/Autograd.py - Gradient optimization
Math_Fundamentals/Optimization:Gradient_Descent - Optimizers
Math_Fundamentals/Optimization:Gradient_Descent/optimizers.py
Data representations
- Dimensionality reduction
Math_Fundamentals/Dimensionality_Reduction - PCA and comparisons
Math_Fundamentals/Dimensionality_Reduction/dim_reduction.py
Other components
- Learner
- Worked output
Connections 22
- Learner → Linear algebra: studies
- Learner → Vector operations: studies
- Learner → Matrix transforms: studies
- Learner → Derivatives: studies
- Learner → Information theory: studies
- Learner → Probability distributions: studies
- Learner → Bayes rule: studies
- Learner → Automatic differentiation: studies
- Learner → Gradient optimization: studies
- Learner → Dimensionality reduction: studies
- Learner → Probability code: runs examples
- Learner → Bayes and classifier: runs examples
- Learner → Entropy code: runs examples
- Learner → Autograd and MLP: runs examples
- Learner → Optimizers: runs examples
- Learner → PCA and comparisons: runs examples
- Probability code → Worked output: prints examples
- Bayes and classifier → Worked output: prints examples
- Entropy code → Worked output: prints examples
- Autograd and MLP → Worked output: prints examples
- Optimizers → Worked output: prints examples
- PCA and comparisons → Worked output: prints examples