Free · 247 Topics · No Signup
Machine Learning Notes
Algorithms, math, Python and real ML projects — written by CodingNow 2.0's mentors. Free to read, structured to actually help you learn.
Machine Learning notes by CodingNow 2.0 cover 247 topics — from what is machine learning? to ml ci/cd — each explained with short definitions, syntax and runnable code examples. They are 100% free, need no signup, and work as quick revision for college exams, Machine Learning interviews and CodingNow 2.0's mentor-led Machine Learning course in Pitampura, Delhi.
ML Fundamentals
What machine learning actually is, how it differs from AI/DL/Data Science, and the ML project lifecycle.
Python for ML
NumPy, Pandas, Matplotlib and scikit-learn — only the parts you actually need for ML.
Mathematics for ML
Linear algebra, calculus and probability — explained with intuition first, formulas second.
Statistics for ML
Descriptive stats, distributions, correlation and hypothesis testing with practical ML examples.
Data Preprocessing
Cleaning, encoding and scaling data correctly — and avoiding data leakage.
Exploratory Data Analysis
Understanding a dataset before modeling it — univariate to multivariate analysis.
Feature Engineering
Creating, transforming and selecting the features that make models work.
Linear Regression
The foundational regression algorithm — equation, cost function and gradient descent.
Logistic Regression
The baseline classification algorithm, built on the sigmoid function.
K-Nearest Neighbors
A simple, instance-based algorithm for classification and regression.
Decision Trees
Gini, entropy, information gain and pruning — how trees split and overfit.
Random Forest
Bagged decision trees — why an ensemble usually beats a single tree.
Support Vector Machines
Margins, support vectors and the kernel trick for linear and non-linear boundaries.
Naive Bayes
Bayes' theorem applied to classification — fast, simple, surprisingly effective.
Clustering & Unsupervised Learning
K-Means, hierarchical clustering and DBSCAN — finding structure without labels.
Dimensionality Reduction
PCA, t-SNE and UMAP — compressing features while keeping signal.
Ensemble Learning
Bagging, boosting and stacking — XGBoost, LightGBM and CatBoost compared.
Model Evaluation
Confusion matrix, precision/recall/F1, ROC-AUC and regression error metrics.
Overfitting & Regularization
Bias-variance tradeoff, L1/L2 regularization and early stopping.
Hyperparameter Tuning
Grid search, random search and Bayesian optimization for model selection.
Imbalanced Data
Why accuracy lies on imbalanced datasets, and how to fix it.
ML Pipelines
scikit-learn Pipeline and ColumnTransformer — reproducible, leak-free workflows.
Explainable ML
SHAP, LIME and permutation importance — interpretability vs explainability.
ML Model Deployment
Saving models and serving predictions with Flask, FastAPI, Streamlit and Docker.
MLOps Fundamentals
Versioning, experiment tracking, monitoring, drift and retraining.
ML System Design
Feature stores, online vs offline inference, and scaling ML systems.
ML Projects
End-to-end builds — EDA through deployment — on realistic datasets.
Interview Questions
Topic-wise ML interview questions with detailed, explained answers.
Practice Questions
Implementation-oriented exercises across preprocessing, modeling and evaluation.
Cheat Sheets
Concise reference pages for algorithms, metrics and scikit-learn syntax.
No notes found. Try a different search term, or browse all Machine Learning notes.
ML Fundamentals
14 of 14 topics publishedWhat Is Machine Learning?
A practical definition of ML, how it differs from traditional programming, and a working code example.
How Machine Learning Works
The represent-predict-measure-improve loop behind every ML algorithm, with a worked example.
Types of Machine Learning
Supervised, unsupervised, semi-supervised, self-supervised and reinforcement learning compared.
Supervised Learning
Regression vs classification, a full scikit-learn example, and when supervised learning applies.
Unsupervised Learning
Clustering and dimensionality reduction explained, with a K-Means customer segmentation example.
Semi-Supervised Learning
How self-training works, and when it beats collecting more labeled data.
Self-Supervised Learning
How models generate their own training labels from raw data, and why it powers modern LLMs.
Reinforcement Learning
The agent-environment-reward loop, and why reward design is the hardest part of RL.
Machine Learning vs AI
Why ML is a subset of AI, not a synonym for it, with a clear containment diagram.
Machine Learning vs Deep Learning
Feature engineering vs automatic feature learning, and when to choose each approach.
Machine Learning vs Data Science
Why data science is the broader discipline, and ML is one tool within it.
ML Workflow
The 10-step technical workflow from problem definition to monitoring, with a full code example.
ML Project Lifecycle
The 5-stage business-facing lifecycle that wraps around the technical ML workflow.
Common Machine Learning Problems
The recurring problem types — regression, classification, clustering, ranking and more — mapped to algorithms.
Python for ML
10 of 10 topics publishedPython for Machine Learning
The core ML Python stack, and which Python concepts you need before starting ML.
NumPy for Machine Learning
Vectorization, broadcasting and axis operations — the NumPy concepts ML code relies on.
Pandas for Machine Learning
Loading, inspecting, filtering and preparing tabular data for scikit-learn.
Matplotlib for Machine Learning
The diagnostic plots ML practitioners actually use — distributions, predicted vs actual, loss curves.
Seaborn for Machine Learning
Correlation heatmaps, boxplots and pairplots for fast, effective EDA.
scikit-learn — The Complete Introduction
The fit/predict/transform API pattern that runs through every scikit-learn model.
NumPy Arrays
Creating, indexing, slicing and reshaping the ndarray — the structure behind every ML feature matrix.
Pandas DataFrame
DataFrame structure, the index, and .loc vs .iloc explained clearly.
Data Loading in Python
Loading CSV, Excel, JSON and SQL data correctly — and avoiding silent dtype and missing-value bugs.
Train-Test Split in Python
The scikit-learn train_test_split function, stratify, random_state, and common leakage mistakes.
Mathematics for ML
20 of 21 topics publishedMath for Machine Learning
The three math pillars behind ML — linear algebra, calculus and probability — and how deep you actually need to go.
Linear Algebra
The building blocks of linear algebra for ML — vectors, matrices, dot products — tied together.
Vectors
What a feature vector represents, vector addition geometrically, and the magnitude formula.
Matrices
Your dataset as a matrix, and how matrix-vector multiplication powers every linear model prediction.
Matrix Multiplication
The formula, a worked example, and why matrix multiplication order matters.
Dot Product
The formula, geometric projection intuition, and where the dot product shows up across ML algorithms.
Eigenvalues
The formula, characteristic equation, and a worked example solving for eigenvalues.
Eigenvectors
Solving for eigenvectors given an eigenvalue, and why PCA components are always orthogonal.
Vector Space
Basis, dimension and span — and how they explain feature space and redundant features.
Calculus for Machine Learning
Why calculus underlies model training, and how derivatives, gradients and the chain rule connect.
Derivatives
The formal definition, power rule, and a tangent-line diagram with a worked example.
Partial Derivatives
Differentiating multivariable functions one variable at a time, with a worked example.
Gradient
The vector of partial derivatives that points toward steepest increase, with a contour-plot diagram.
Gradient Descent
The core training algorithm behind most ML models, with a step-by-step numerical trace and learning rate comparison.
Chain Rule
The formula, a worked example, and why it powers backpropagation.
Probability for Machine Learning
Core probability definitions and formulas, and why ML reasons in probabilities rather than certainties.
Random Variables
Discrete vs continuous random variables, notation, and a coin-flip example.
Probability Distributions
Bernoulli, Binomial and Normal distributions, with formulas and a bell curve diagram.
Conditional Probability
The formula, a Venn diagram, and a worked spam-email example.
Expectation
The expected value formula, linearity of expectation, and a dice-roll example.
Statistics for ML
6 of 17 topics publishedStatistics for Machine Learning
Descriptive vs inferential statistics, and why skipping stats causes real ML mistakes.
Mean
The mean as a balance point, population vs sample formulas, and why it can mislead on skewed data.
Median
The median as a rank-based, outlier-resistant summary, with odd/even-count worked examples.
Mode
The only central tendency measure for categorical data, with unimodal/bimodal intuition.
Variance
Why deviations are squared, population vs sample formulas, and Bessel's correction explained.
Standard Deviation
Why we take the square root of variance, the 68-95-99.7 rule, and Python implementation.
Data Preprocessing
16 of 16 topics publishedData Preprocessing
The standard preprocessing sequence — cleaning, encoding, scaling — and why order matters.
Data Cleaning
Fixing dtype, text and structural issues before deeper preprocessing.
Missing Values
MCAR, MAR and MNAR — why the type of missingness determines whether imputation is safe.
Missing Value Imputation
Mean, median, mode and KNN imputation compared, with a worked skewed-data example.
Duplicate Data
Detecting and removing exact and near-duplicate rows correctly.
Outlier Treatment
IQR and Z-score outlier detection formulas, a boxplot diagram, and how to treat outliers.
Categorical Data
Nominal vs ordinal categories, and why cardinality decides your encoding strategy.
Label Encoding
How LabelEncoder works, and why using it on nominal features implies a false order.
One-Hot Encoding
How one-hot encoding works, the dummy variable trap, and handling unseen categories in production.
Ordinal Encoding
Encoding genuinely ordered categories while preserving their real-world rank.
Feature Scaling
Why scale matters for distance- and gradient-based models, with a before/after diagram.
Standardization
The Z-score formula, a worked example, and why it's the default scaling choice.
Normalization
The Min-Max formula, a worked example, and normalization vs standardization.
Robust Scaling
Median/IQR-based scaling that resists outliers, with a worked numerical example.
Data Leakage
Preprocessing, target and temporal leakage — how each happens and how to prevent it.
Preprocessing Pipeline
Chaining imputation, encoding and scaling into a single reproducible scikit-learn pipeline.
Exploratory Data Analysis
7 of 10 topics publishedExploratory Data Analysis (EDA)
The full EDA workflow — shape/quality checks through univariate, bivariate and multivariate analysis.
Univariate Analysis
Analyzing one variable at a time — distribution shapes, skew, and turning findings into preprocessing decisions.
Bivariate Analysis
Numeric-numeric, numeric-categorical and categorical-categorical relationship analysis.
Multivariate Analysis
Analyzing 3+ variables together — pairplots, correlation heatmaps, and feature interactions.
Correlation Analysis
The Pearson correlation formula, a hand-worked example, and correlation vs causation.
Boxplot Analysis
Fully annotated boxplot anatomy, and boxplot vs histogram — when to use each.
EDA for Machine Learning
A direct decision table mapping common EDA findings to concrete preprocessing and modeling actions.
Feature Engineering
15 of 18 topics publishedFeature Engineering
Creating, transforming and selecting features — and why it often matters more than algorithm choice.
Feature Selection
The filter, wrapper and embedded families of feature selection compared.
Feature Extraction
Deriving new, compact features from raw or complex data — PCA, aggregation and text vectors.
Feature Transformation
Log, square root and Box-Cox transforms for fixing skewed numeric features.
Numerical Features
Binning, ratios and other numeric feature engineering techniques beyond basic scaling.
Categorical Features
Frequency encoding, target encoding, and handling rare/high-cardinality categories.
Date-Time Features
Extracting calendar features and cyclical sine/cosine encoding for time-based data.
Text Features
Bag-of-Words, the TF-IDF formula, and simple statistical text features.
Polynomial Features
How polynomial expansion lets linear models fit curves, with a full worked example.
Interaction Features
Capturing combined feature effects a linear model can't discover on its own.
Feature Importance
Three ways to measure feature importance, and why they can disagree.
Feature Engineering Best Practices
A practical checklist and before/after example for disciplined feature engineering.
Filter Methods
Variance threshold and correlation-based feature selection, with formulas and code.
Wrapper Methods
Recursive Feature Elimination (RFE) explained step by step, with scikit-learn code.
Embedded Methods
Lasso regularization and tree-based importance as automatic feature selection.
Linear Regression
9 of 9 topics publishedLinear Regression
The equation, geometric intuition, simple vs multiple, and how the model is trained.
Simple Linear Regression
The full coefficient formula, hand-worked example, and residual calculation.
Multiple Linear Regression
Fitting a plane through multiple features, and why coefficients mean something different here.
Linear Regression Cost Function
The MSE formula, why squared error, and why the cost surface is a convex bowl.
Linear Regression with Gradient Descent
Deriving the exact gradient formulas and a from-scratch training loop.
Linear Regression Assumptions
The five assumptions, how to check each with a diagram, and what to do when one is violated.
Linear Regression in Python
A complete scikit-learn workflow plus a from-scratch Normal Equation implementation.
Linear Regression Example
A full apartment-rent case study focused on interpreting coefficients for a business audience.
Linear Regression Interview Questions
Eight commonly asked linear regression interview questions with detailed answers and tips.
Logistic Regression
7 of 7 topics publishedLogistic Regression
The equation, decision boundary diagram, and full overview of the standard classification baseline.
Logistic Regression Intuition
Why linear regression fails at classification, and the log-odds interpretation of the coefficients.
Sigmoid Function
The formula, S-curve diagram, derivative, and a worked numerical example.
Logistic Regression Cost Function
The log-loss formula, why it stays convex, and a worked example comparing good vs bad predictions.
Logistic Regression in Python
A complete scikit-learn workflow, threshold tuning, and multi-class classification.
Logistic Regression Example
A full loan default risk case study, from EDA to a business decision layer.
Logistic Regression vs Linear Regression
A direct side-by-side comparison, what they share, and how to choose between them.
K-Nearest Neighbors
8 of 9 topics publishedK-Nearest Neighbors (KNN)
The core idea, lazy learning, and a full overview of the KNN algorithm.
How KNN Works
A complete hand-worked example — every distance computed, sorted, and voted on.
KNN Distance
Euclidean, Manhattan and Minkowski distance formulas, with a diagram and worked example.
Choosing k in KNN
The bias-variance tradeoff of k, with a U-shaped error diagram and cross-validation code.
KNN Classification
Majority voting, jagged decision boundaries, and distance-weighted voting.
KNN Regression
Predicting continuous values by averaging neighbors, with a full worked example.
KNN in Python
A complete pipeline with scaling and cross-validated k-tuning for classification and regression.
KNN Advantages & Disadvantages
A focused pros/cons breakdown, including the curse of dimensionality explained with code.
Decision Trees
9 of 9 topics publishedDecision Tree
Tree structure, terminology, and how a tree decides where to split.
Decision Tree Classification
A full worked example of choosing the first split using Gini and entropy.
Decision Tree Regression
Variance-reduction splitting and leaf-mean prediction, with a worked example.
Gini Impurity
The formula, an impurity curve diagram, and a worked calculation.
Entropy
The information-theoretic formula, a curve comparison with Gini, and a worked example.
Information Gain
The formula and a complete worked calculation showing how a tree picks its best split.
Decision Tree Pruning
Pre-pruning vs post-pruning (cost-complexity), with a full-tree vs pruned-tree diagram.
Decision Tree in Python
A complete workflow with tree visualization, feature importance, and rule extraction.
Decision Tree Overfitting
Why trees overfit so readily, a train-vs-validation diagram, and the fixes in order.
Random Forest
7 of 7 topics publishedRandom Forest
The ensemble idea, bagging and random feature subsets, and a voting diagram.
How Random Forest Works
Bootstrap sampling, random feature subsets, and out-of-bag samples explained with the math.
Random Forest Classification
Majority voting, the probability formula, and why the ensemble boundary is more stable.
Random Forest Regression
Averaging tree predictions, with a worked example and Python implementation.
Random Forest Feature Importance
The Mean Decrease in Impurity formula, and its known bias toward high-cardinality features.
Random Forest in Python
A complete workflow with OOB scoring, hyperparameter tuning, and parallelized training.
Random Forest vs Decision Tree
A direct comparison table and the bias-variance story behind why forests usually win.
Support Vector Machines
9 of 10 topics publishedSupport Vector Machine (SVM)
The maximum-margin idea, the decision boundary formula, and a worked example.
SVM Classification
The hard and soft margin optimization problems, and the role of the C hyperparameter.
SVM Margin
The margin formula, why minimizing ||w|| maximizes it, and a full worked example.
Support Vectors
Which points become support vectors, and why only they determine the boundary.
Kernel Trick
How SVM handles non-linear data without explicit feature transformation.
Linear Kernel
The simplest kernel, and when it beats non-linear alternatives (like for text data).
RBF Kernel
The Gaussian kernel formula, the gamma hyperparameter, and a worked numerical example.
SVM in Python
A complete workflow with joint kernel/C/gamma tuning and SVR for regression.
SVM Advantages & Disadvantages
A focused pros/cons breakdown and a direct comparison with logistic regression and Random Forest.
Naive Bayes
6 of 7 topics publishedNaive Bayes
Bayes' theorem applied to classification, the independence assumption, and a full worked example.
Gaussian Naive Bayes
The normal-distribution likelihood formula, with a full worked pass/fail example.
Multinomial Naive Bayes
The word-count formula, Laplace smoothing, and a full worked text example.
Bernoulli Naive Bayes
The binary presence/absence formula, and how it differs from Multinomial NB.
Naive Bayes for Text Classification
A full spam-filter workflow from raw text to a trained, inspectable model.
Naive Bayes in Python
All three NB variants compared side by side, with a decision table and tuning workflow.
Clustering & Unsupervised Learning
10 of 12 topics publishedClustering
The idea of grouping data with no labels, and the three main clustering approaches.
K-Means
The WCSS objective formula, the algorithm steps, and a full hand-worked example.
K-Means Elbow Method
Choosing k by finding the point of diminishing WCSS returns, with a diagram.
K-Means in Python
A complete workflow with scaling, elbow + silhouette for choosing k, and visualization.
Hierarchical Clustering
Agglomerative vs divisive, dendrograms, and a full worked merging example.
Agglomerative Clustering
The bottom-up merging algorithm in code, with linkage criteria compared.
DBSCAN
Core, border and noise points, the algorithm steps, and why it handles irregular shapes.
DBSCAN in Python
A complete workflow comparing DBSCAN vs K-Means on non-convex cluster shapes.
Clustering Evaluation
Internal vs external metrics, and why numeric scores alone aren't enough.
Silhouette Score
The formula, a full hand-worked example, and how to use it to choose k.
Dimensionality Reduction
8 of 9 topics publishedDimensionality Reduction
Why fewer dimensions can mean more signal, and the two main families of techniques.
PCA (Principal Component Analysis)
The eigenvalue formula, geometric intuition, and a full hand-worked example.
PCA Step by Step
The complete 5-step algorithm, hand-computed from covariance matrix to projection.
PCA in Python
A complete workflow with scree plots, 2D visualization, and reconstruction.
PCA vs Feature Selection
The interpretability tradeoff between new combined features and original features.
t-SNE
Non-linear, neighborhood-preserving visualization, and its critical interpretation limits.
UMAP
How UMAP compares to t-SNE, and why it supports transforming new data.
Dimensionality Reduction Use Cases
Six concrete use cases, and a decision guide for whether you need it at all.
Ensemble Learning
11 of 11 topics publishedEnsemble Learning
The four main ensemble families, and why bagging vs boosting reduce different types of error.
Bagging
Bootstrap Aggregating's variance-reduction formula, generalized beyond Random Forest.
Boosting
The general sequential error-correction pattern behind AdaBoost and Gradient Boosting.
Stacking
Training a meta-model to learn the best combination of diverse base models.
Voting Classifier
Hard vs soft voting, with worked examples and weighted voting.
AdaBoost
The full weight-update formula, computed by hand across one complete round.
Gradient Boosting
Fitting residuals round by round, with a full worked numerical example.
XGBoost
What XGBoost adds beyond plain gradient boosting, with regularization and early stopping.
LightGBM
Leaf-wise vs level-wise tree growth, and why it's built for speed on large data.
CatBoost
Native categorical feature handling and ordered boosting explained.
Random Forest vs Boosting
A direct comparison and practical decision framework for choosing between them.
Model Evaluation
19 of 19 topics publishedModel Evaluation
The full evaluation workflow, and why classification and regression need different metrics.
Train-Test Split (Concept)
Why one split isn't always reliable, and the three-way train/validation/test setup.
Cross-Validation
Averaging performance across multiple splits, with the mean and std formulas.
K-Fold Cross-Validation
The rotating-fold algorithm, with a diagram and full Python implementation.
Stratified K-Fold
Preserving class proportions per fold, essential for imbalanced classification.
Confusion Matrix
TP/TN/FP/FN defined, with a full worked example and diagram.
Accuracy
The formula, a worked example, and why it's dangerously misleading on imbalanced data.
Precision
The formula, a worked example, and when false positives are the costly error.
Recall
The formula, a worked example, and the trap of trivially maximizing it.
F1-Score
The harmonic mean formula, a worked example, and why it beats a plain average.
ROC-AUC
TPR/FPR, the ROC curve diagram, and a worked threshold-by-threshold example.
Precision-Recall Curve
Why it beats ROC-AUC on imbalanced data, with threshold-selection code.
Log Loss
Evaluating probability calibration, not just correctness, with a worked comparison.
Mean Squared Error
The MSE formula, a worked example, and why squaring creates a units problem.
Mean Absolute Error
The MAE formula, a worked example, and a direct outlier-sensitivity comparison to MSE.
RMSE
The square-root-of-MSE formula, a worked example, and why it's the most-reported metric.
R² Score
The variance-explained formula, a worked example, and why R² can go negative.
Classification Metrics
A decision table for choosing between accuracy, precision, recall, F1 and ROC-AUC.
Regression Metrics
A decision table for choosing between MSE, MAE, RMSE and R².
Overfitting & Regularization
9 of 9 topics publishedOverfitting
The train/validation gap signal, common causes, and the full list of fixes.
Underfitting
The opposite failure mode — poor scores on both training and validation data.
Bias
The formal definition of model bias, and why more data can't fix it.
Bias-Variance Tradeoff
The full decomposition formula, a U-shaped diagram, and a 3-model worked comparison.
Regularization
The general penalty formula, and why penalizing large coefficients prevents overfitting.
L1 Regularization
The soft-thresholding formula, worked example, and the geometric reason it zeroes coefficients.
L2 Regularization
The shrinkage formula, worked example, and why it handles correlated features better than L1.
Elastic Net
Combining L1 and L2, and why it fixes Lasso's instability with correlated features.
Early Stopping
The algorithm, a diagram, and implementations for XGBoost and neural networks.
Hyperparameter Tuning
7 of 7 topics publishedHyperparameter Tuning
The three main search strategies compared, and why tuning matters.
Grid Search
The exhaustive search formula, a worked example, and why it explodes with dimensions.
Random Search
Why random sampling often beats grid search, with a coverage diagram.
Bayesian Optimization
Using past trials to intelligently search, with an Optuna implementation.
Hyperparameter vs Parameter
A clear table distinguishing the two, with examples across every major algorithm.
Model Selection
Comparing algorithms fairly, by tuning each one before comparing.
Cross-Validation for Hyperparameter Tuning
Nested cross-validation, and why GridSearchCV's best_score_ can be optimistic.
Imbalanced Data
6 of 7 topics publishedImbalanced Data
Why accuracy lies on skewed datasets, and the three families of fixes.
Oversampling
Duplicating minority examples, with the overfitting-to-duplicates risk explained.
Undersampling
Reducing majority examples, with Tomek Links as a smarter alternative to random removal.
SMOTE
The synthetic interpolation formula, a full worked example, and a diagram.
Class Weights
The balanced-weighting formula, a worked example, and custom cost-based weights.
Imbalanced Classification Metrics
Balanced Accuracy and MCC formulas, both worked from the same confusion matrix.
ML Pipelines
6 of 6 topics publishedML Pipeline
The end-to-end pipeline concept, its stages, and the three concrete benefits.
scikit-learn Pipeline
The Pipeline class mechanics — named steps, indexing, and grid search integration.
ColumnTransformer
Applying different preprocessing to different columns, and the remainder trap.
Feature Engineering Pipeline
Custom transformers with FunctionTransformer and BaseEstimator/TransformerMixin.
Model Training Pipeline
The full orchestration from split to tuning to saving one deployable pipeline.
Pipeline & Data Leakage
How Pipeline mechanically prevents leakage during cross-validation, step by step.
Explainable ML
6 of 6 topics publishedExplainable AI
Why explainability matters, the interpretability-accuracy tension, and the technique toolbox.
Model Interpretability
The precise distinction between interpretability and explainability, with examples.
Permutation Importance
The shuffle-and-measure algorithm, a worked example, and why it fixes MDI's bias.
SHAP
The Shapley value formula, a full hand-worked 2-feature example, and Python code.
LIME
Local surrogate models explained, with a direct comparison to SHAP.
Global vs Local Explanations
A clear table of which techniques serve which scope, and how to choose.
ML Model Deployment
10 of 10 topics publishedML Model Deployment
The deployment landscape, and batch vs real-time inference.
Saving an ML Model
joblib vs pickle, what to save beyond the model, and the security warning.
joblib
Why joblib beats pickle for NumPy-heavy models, with compression and bundling.
Pickle for ML
The full security explanation of arbitrary code execution via untrusted pickle files.
ML API
Request/response design, versioning, and input validation for serving predictions.
Flask ML API
A complete Flask implementation serving a model, with input validation.
FastAPI ML API
A complete FastAPI implementation with automatic Pydantic validation.
Streamlit for ML
Building an interactive model demo app, with caching and visualization.
Docker for ML Models
A complete Dockerfile, version pinning, and multi-stage builds.
ML Inference
Train-serve skew, loading models once, and efficient batch prediction.
MLOps Fundamentals
11 of 11 topics publishedMLOps
What MLOps is, why it exists, and four key comparisons that define it.
MLOps Lifecycle
The full 14-stage pipeline diagram, and how it differs from the ML workflow and project lifecycle.
Model Versioning
What to version, semantic versioning for models, and MLflow implementation.
Data Versioning
Why Git alone doesn't work for data, and DVC implementation.
Model Registry
Staging, production and archived model stages, with MLflow Model Registry.
Experiment Tracking
Logging every training run's parameters and metrics with MLflow.
ML Monitoring
What to monitor beyond uptime, and the delayed-label problem.
Model Drift
The umbrella term for degradation, the PSI formula, and a full worked example.
Data Drift
Detecting input distribution shift with the KS test and chi-squared test.
ML Retraining
The three retraining triggers, and a full retraining pipeline with a quality gate.
ML CI/CD
The three C's of ML CI/CD, and a complete GitHub Actions workflow.
More Machine Learning Notes
1 topicsReady to go from notes to a real career?
Join CodingNow 2.0's Machine Learning course — live mentorship, hands-on projects, and 100% placement support in Delhi NCR.
Enroll Now — Free Demo AvailableMachine Learning Notes – FAQs
What students search before reading Machine Learning notes.
