@datascibykashi: If you’re learning Machine Learning, don’t memorize formulas blindly. Understand what each formula measures, when it is used, and what problem it solves. Here’s a practical ML formula cheat sheet 👇 📊 1. STATISTICS Mean μ = (1/n) Σxᵢ Variance σ² = (1/n) Σ(xᵢ − μ)² Standard Deviation σ = √σ² Z-Score z = (x − μ) / σ Covariance Cov(X,Y) = Σ[(xᵢ−μₓ)(yᵢ−μᵧ)] / n Correlation r = Cov(X,Y) / (σₓσᵧ) 🎯 2. PROBABILITY Conditional Probability P(A|B) = P(A∩B) / P(B) Bayes’ Theorem P(A|B) = P(B|A)P(A) / P(B) Independence P(A∩B) = P(A)P(B) 📈 3. LINEAR REGRESSION Prediction ŷ = β₀ + β₁x Multiple Linear Regression ŷ = β₀ + β₁x₁ + β₂x₂ + ... + βₚxₚ Mean Squared Error MSE = (1/n) Σ(yᵢ−ŷᵢ)² Root Mean Squared Error RMSE = √MSE Mean Absolute Error MAE = (1/n) Σ|yᵢ−ŷᵢ| 🔐 4. LOGISTIC REGRESSION Sigmoid Function σ(z) = 1 / (1 + e⁻ᶻ) Log-Odds log(p/(1−p)) = β₀ + β₁x Binary Cross-Entropy L = −[y log(ŷ) + (1−y)log(1−ŷ)] 📉 5. GRADIENT DESCENT Parameter Update θ ← θ − α∇J(θ) Where: α = Learning Rate ∇J(θ) = Gradient The goal is to move the parameters toward lower loss. ⚖️ 6. REGULARIZATION L1 / Lasso Loss = MSE + λΣ|wᵢ| L2 / Ridge Loss = MSE + λΣwᵢ² Elastic Net Loss = MSE + λ₁Σ|wᵢ| + λ₂Σwᵢ² 🌳 7. DECISION TREES Entropy H(S) = −Σpᵢlog₂(pᵢ) Information Gain IG = H(parent) − Σ(weight × H(child)) Gini Impurity Gini = 1 − Σpᵢ² 📏 8. DISTANCE METRICS Euclidean Distance d = √Σ(xᵢ−yᵢ)² Manhattan Distance d = Σ|xᵢ−yᵢ| Minkowski Distance d = (Σ|xᵢ−yᵢ|ᵖ)¹⁄ᵖ Cosine Similarity cos(θ) = (A·B)/(||A||||B||) 🎯 9. CLASSIFICATION METRICS From the confusion matrix: Accuracy (TP + TN)/(TP + TN + FP + FN) Precision TP/(TP + FP) Recall TP/(TP + FN) Specificity TN/(TN + FP) F1 Score 2 × (Precision × Recall)/(Precision + Recall) 📊 10. CLUSTERING K-Means Objective J = Σ||xᵢ−μcᵢ||² The algorithm tries to minimize the distance between data points and their assigned cluster centers. 🧮 11. PCA Covariance Matrix Σ = (1/n)XᵀX Eigenvalue Equation Σv = λv PCA finds directions that capture maximum variance. 🧠 12. NEURAL NETWORKS Linear Transformation z = Wx + b ReLU f(x) = max(0,x) Sigmoid f(x) = 1/(1+e⁻ˣ) Softmax P(y=i) = eᶻⁱ / Σeᶻʲ 🔥 13. DEEP LEARNING LOSSES Binary Cross-Entropy L = −[y log(ŷ)+(1−y)log(1−ŷ)] Categorical Cross-Entropy L = −Σ yᵢlog(ŷᵢ) Mean Squared Error MSE = (1/n)Σ(yᵢ−ŷᵢ)² 📐 14. OPTIMIZATION Momentum vₜ = βvₜ₋₁ + (1−β)∇J(θ) Adam Adam combines momentum-like first-moment tracking with second-moment tracking to adapt parameter updates. 🚀 THE ML MATH ROADMAP Statistics ↓ Probability ↓ Linear Algebra ↓ Calculus ↓ Optimization ↓ Machine Learning Algorithms ↓ Deep Learning 💡 Don’t try to memorize this entire list. Understand the intuition behind each formula and know where it appears in an ML workflow. 📌 Save this as your Machine Learning Formula Cheat Sheet. #MachineLearning #DataScience #ML #creatorsearchinsights #datascience

Data Scientist | Kashi

Open In TikTok:

Region: PK

Tuesday 22 September 2026 05:45:38 GMT