vijayanant

Curriculum: Mathematical Foundations of AI

This is a personalized, self-paced roadmap for mastering the mathematical foundations of Machine Learning (ML) and Artificial Intelligence (AI). It is designed to build a strong "intuition-first" theoretical base, immediately backed by practical Python/NumPy implementations and empirical experiments.

Primary Theoretical Sources & Video Series

1. [MFML] Mathematical Foundations of Machine Learning by Prof. Prathosh AP (IISc)
2. [PF] Probability Foundations by Prof. Krishna Jagannathan (IIT Madras)
3. [Prathosh-Prob] Probability Theory by Prof. Prathosh (IISc)
4. [3B1B-LA] 3Blue1Brown: Essence of Linear Algebra

vijayanant

def can_user_act_on_document(user, document, action):
    if user.is_admin:
        return True
    if action == "view":
        return document.owner_id == user.id
    if action == "edit":
        return document.owner_id == user.id
    return False  # unknown action

# growing conditionals and nested logic

vijayanant

trait Summable {
    fn zero() -> Self;
    fn add(&self, other: &Self) -> Self;
}

impl Summable for i32 {
    fn zero() -> Self {
        0
    }
    fn add(&self, other: &Self) -> Self {

vijayanant

# Problem Statement 
# cons(a, b) constructs a pair, and car(pair) and cdr(pair) returns the first and last element of that pair.
# For example, car(cons(3, 4)) returns 3, and cdr(cons(3, 4)) returns 4.
# Given the below implementation for cons( ), please implement car & cdr

def cons(a, b):
  def pair(f):
    return f(a, b)
  return pair

vijayanant

data Point = Pt Int Int
data Expr a = Number Integer | Boolean Bool

vijayanant

Git Branching and Realeasing

AIM

To make below listed activites simple (from SCM point of view)

• Adding new features
• Fixing bugs
• Preparing for release
• Deploying to production
• Applying hotfixes
• Versioning

vijayanant

Haskell Resources

• Learning Haskell
• Learn You a Haskell for Great Good
  • Learn You A Haskell Exercises
• Real World Haskell
• FPComplete's School of Haskell
• Haskell Wikibook
• Write Yourself a Scheme in 48 Hours
• Parallel and Concurrent Programming in Haskell

vijayanant

{-# LANGUAGE TypeFamilies
           , DataKinds
           , PolyKinds
           , TypeInType
           , TypeOperators
           , UndecidableInstances
           , RankNTypes
  #-}

vijayanant

A List of Foundational Haskell Papers

The Beginning: The Eugenio Moggi Papers

• Notions of Computations over Monads
• Computational Lambda Calculus and Monads
• Monads for functional programming

Haskell Semantics and Design Spaces

vijayanant

{-# LANGUAGE RankNTypes #-}

module RankN where

-- Rank 0: 
-- add1 is momomorphic
add1 :: Int -> Int
add1 x = x + 1

-- Rank 1