# Machine Learning Notes

I have been an avid learner of statistics and machine learning. My primary reason for exploring them has been the ability to apply them to use-cases cutting across different domains and problems. Primary interest though pertains to the market place, trading, pricing, optimisation problems.

I have had the opportunity to explore healthcare, trading and sports analytics in the form of cricket, where I have been able to both formulate and solve a bunch of interesting problems end to end. These notes try to pen down the intuition behind several of those questions. The notes link is embedded in the Title itself.

Questions : Machine Learning Basics

• Convex and Non Convex Problems ?
• Relationship between Rate Of Learning and Step Size ?

Data Modelling

• Feature selection, transformation and extraction
• Learning vs Memoization ?
• What is the assumption behind IID, stationarity and same sample data ?
• Train vs Validation vs Test Sets ?

Feature Regularisation

• Feature Representation
• What is Multi-Collinearity ?
• Bias Vs Variance Trade Off ?
• Lasso vs Ridge Regression ?

Algorithms

• Bagging vs Boosting ?
• Boosting Base Models
• Logit Function
• Better Data vs Better Model ?

Machine Learning Essentials

Hessian Matrix

• Hessian Matrix vs Gradient Descent
• Formula

Variance

• Derivation
• Correlation vs Covariance
• Covariance as graph

Eigen Values

• Eigen Values Intuition
• Eigen Value Vector
• Eigen Value as Hinge

Laplace Transformation

• Laplace Transformation Intuition
• Transformation as a tool

Lagrange Multipliers

• Lagrange Multiplier Intuition
• Constrained Optimisation Problem

Data Science with R (Scheduling using Optrees)

• DAG
• Shortest Path Algorithm
• Encoding the Problem as DAG
• Solving using Optrees

Machine Learning Regression (Interpretation)

• Null Hypothesis
• Significane vs Non Significance
• Intercept
• Interpretation

In the process, I would often end of re-using similar problem-solving approaches and often wanted to remember all the cool tricks/hacks and hard-learned concepts I have had been able to work-out all these years.

Auquan Financial Time Series

And several other contests during campus days !!

Besides improving your odds of winning these, I decided to write some notes to help collate concepts and takeaways from ML in an intuitive fashion. If you are one of those guys who love diagrams and intuition over maths to better understand stuff, you would love them.

In case of any doubts or questions, feel free to reach out below!!