#MathForAI

📘 Day 15: AI/ML Journey 🔹 Math → Probability & Statistics • LLN → sample mean → true mean as trials ↑ • CLT → sample means ≈ Normal distribution 📊 These are the backbone of statistical inference in ML. Step by step 🚀 #AI #MachineLearning #MathForAI #MumInTech

📘 Day 5: AI/ML Journey Motherhood comes first ❤️ Today I spent most of the day caring for my sick child. Still, while waiting at the hospital, I managed to cover:
 🔹 Math → Inverse of a 3×3 matrix Not every day will be a big win, but consistency matters 🚀 #MathForAI

📘 Day 14: AI/ML Journey 🔹 Math → Correlation 🔹 Weekly Review • Probability basics • Conditional Probability & Bayes • Random Variables • Distributions (Binomial, Poisson, Normal) • Mean, Variance, Std Dev Covariance & Correlation #AI #MachineLearning #MathForAI

Kicked off my AI journey with Linear Algebra! @3Blue1Brown's Essence of Linear Algebra is an absolute game-changer—making complex concepts crystal clear! #AI #LinearAlgebra #MathForAI

Foundations of AI Math Free Beginner Course #AI #MathForAI #FreeCourse

📘 Day 11: AI/ML 🔹 Math → Probability Distributions • Binomial → successes in fixed trials • Poisson → rare events • Normal → bell curve 📈 🔹 Python → Loops • for loop • while loop From math models to coding logic—step by step 🚀 #AI #MachineLearning #MathForAI

Day 16 of my AI Journey 🚀 Today I explored Matrix Operations – the backbone of Machine Learning & Deep Learning! 📌 Addition, Multiplication, Transpose, Inverse #100DaysOfAI #MachineLearning #MathForAI

📘 Day 23: AI/ML Journey 🔹 Math → Calculus • Continuity • Derivatives • Differentiation Rules (power, product, quotient, chain) Derivatives = foundation of optimization in ML. Step by step 🚀 #AI #MachineLearning #MathForAI #Calculus #MumInTech

📘 Day 20: AI/ML Journey 🔹 Math → Statistical Distributions • Gaussian (Normal) → bell curve, core to ML models • Multinomial → outcomes w/ multiple categories (e.g., NLP word counts) Distributions = backbone of probabilistic AI 🚀 #AI #MachineLearning #MathForAI

📘 Day 24: AI/ML Journey 🔹 Math → Calculus • Partial Derivatives → change w.r.t one variable • Gradients → vector of partial derivatives, used in optimization Gradients = the heartbeat of ML learning 🚀 #AI #MachineLearning #MathForAI #Calculus #MumInTech

📘 Day 27: AI/ML Journey 🔹 Math → Hessian Matrix = 2nd-order partial derivatives 🔹 Second Derivative Test → tells if a point is min, max, or saddle Critical for optimization in ML 🚀 #AI #MachineLearning #MathForAI #Optimization #MumInTech

📘 Day 13: AI/ML Journey 🔹 Math → Statistics • Covariance = how 2 variables change together 👉 +ve: rise together 👉 -ve: one rises, other falls Couldn’t cover correlation today (busy w/ home + client work). Will continue tomorrow. Step by step 🚀 #AI #MathForAI

📘 Day 9: AI/ML Journey 🔹 Math → Probability • Conditional Probability • Bayes’ Theorem (update beliefs w/ new evidence) Abstract at first, but real-world examples (medical tests, spam filters) make it click 💡 Step by step 🚀 #AI #MachineLearning #MathForAI #MumInTech

How is math the backbone of AI? 🤔 Join us on January 15 at 10 AM PDT with Albar Wahab for a beginner-friendly webinar exploring how mathematics drives artificial intelligence. RSVP now: #MathForAI #VectorEmbeddings #VectorSimilarity #CosineSimilarity

📘 Day 22: AI/ML Journey Didn’t do much today, but made a start with Limits (foundation of calculus & optimization in ML). Not every day is heavy, but showing up matters 🚀 #AI #MachineLearning #MathForAI #MumInTech

How is math the backbone of AI? 🤔 Join our webinar, Simplifying Mathematics Behind AI, with Albar Wahab, Senior Data Scientist at Data Science Dojo on January 15 at 10am PDT. RSVP now: #MathForAI #VectorEmbeddings #VectorSimilarity #CosineSimilarity

Day 10: AI/ML Journey 🔹 Math → Probability • Discrete RVs → countable values (e.g., dice rolls 🎲) • Continuous RVs → any value in a range (e.g., height 📏) They form the basis of probability distributions in ML 💡 Step by step 🚀 #AI #MachineLearning #MathForAI

📘 Day 19: AI/ML Journey 🔹 Math → Probability • PDF → likelihood of values (for continuous variables) • CDF → probability a variable ≤ value PDFs = shape of distribution, CDFs = accumulated probability 💡 Step by step 🚀 #AI #MachineLearning #MathForAI m #MumInTech

Day 13 of AI Journey 🚀 Linear Algebra Basics 🔢 → Scalars, Vectors, Matrices → Operations (Add, Multiply, Transpose) #100DaysOfAI #MathForAI