AI & Computer Science

Machine Learning Simulators

A focused AI & Computer Science hub for machine learning tools, keeping related formulas, assumptions, and engineering checks together.

45 simulators

Adjacent categories

Math & Numerical Methods Controls & Robotics V&V, Quality & Reliability Biomedical Engineering

Simulator list

AdaBoost Simulator — Boosting Weak Classifiers
Machine Learning
For 2D data, run AdaBoost for T iterations using depth-1 decision stumps as weak classifiers. Visualize sample weights and the final strong classifier's decision boundar…
Adam Optimizer Simulator
Machine Learning
Experience Adam, the workhorse algorithm behind deep-learning training.
1D Linear Autoencoder Simulator — Compression Equivalent to PCA
Machine Learning
Compress a 10-dim signal through a K-dim bottleneck and decode it linearly. After SGD training a linear AE behaves like PCA on the top K principal components.
Batch Normalization Simulator
Machine Learning
Visualize batch normalization, the technique that stabilizes the training of deep neural networks.
Bias-Variance Tradeoff Simulator
Machine Learning
A tool that decomposes the generalisation error of machine learning into three parts — bias², variance and noise. Change the degree of the polynomial model and watch, in…
Collaborative Filtering Simulator
Machine Learning
Explore the recommendation algorithm behind "customers who bought this also bought…" — collaborative filtering.
Confusion Matrix Metrics Simulator
Machine Learning
Confusion Matrix Metrics Simulator updates live numeric results and charts as inputs change, supporting early design checks and model review.
Cross-Entropy vs MSE Loss Simulator
Machine Learning
A tool to feel why binary classification uses cross-entropy rather than mean squared error (MSE). Move the input logit z to the sigmoid and the true label y, and both lo…
k-Fold Cross-Validation Simulator
Machine Learning
An interactive view of how k-fold cross-validation estimates a model's ability to generalize to unseen data.
DBSCAN Simulator — Density-Based Clustering
Machine Learning
Apply DBSCAN to 2D scatter data in real time. Change ε and MinPts to learn how core, border and noise points are classified and how arbitrary-shaped clusters emerge.
Decision Analysis & Expected Value Calculator — EMV & Decision Tree
Machine Learning
Calculate Expected Monetary Value (EMV) and visualize decision trees. Use our tool for probability distributions and tornado sensitivity analysis in decision-making.
Decision Tree Impurity — Gini, Entropy and Misclassification
Machine Learning
Compare three impurity measures used in two-class decision trees on a single chart. Move the class ratio and split to see why CART uses Gini and why misclassification is…
Dropout Regularization Simulator
Machine Learning
Explore "dropout", the technique that curbs overfitting in neural networks.
Elastic Net Regression Simulator
Machine Learning
Move the L1/L2 mixing ratio α and the regularization strength λ in the Elastic Net estimator (Zou & Hastie 2005) and watch the number of selected features, the effec…
Gaussian Process Regression — RBF Kernel & 95% Confidence Band
Machine Learning
Visualize 1D GP regression in real time. Adjust data count, length scale, signal variance and noise to learn how Bayesian uncertainty estimates behave.
Genetic Algorithm Optimizer
Machine Learning
Run GA optimization on Rastrigin, Ackley, Sphere, and Rosenbrock functions. Watch population evolve on fitness landscape.
Gradient Boosting Simulator
Machine Learning
Gradient boosting builds a strong predictor by fitting shallow regression trees — "weak learners" — to the residuals one at a time and adding them up. Adjust the number …
Gradient Clipping Simulator
Machine Learning
Explore gradient clipping, the standard fix for exploding gradients in deep learning.
Gradient Descent with Momentum Simulator
Machine Learning
Experience the optimization algorithms behind machine-learning training.
Gradient Descent Optimizer Visualizer — SGD, Adam, RMSprop
Machine Learning
Visualize how SGD, Adam, and RMSprop navigate 2D loss landscapes in real time. Understand machine learning optimization algorithms interactively.
Hierarchical Clustering Simulator — Agglomerative & Dendrogram
Machine Learning
Hierarchical clustering simulator with live dendrogram. Switch single/complete/average linkage and cut at a distance threshold to control cluster count.
Image Convolution Kernel Simulator
Machine Learning
Experience the "convolution" that filters an image with a 3x3 kernel.
K-Fold Cross-Validation Simulator — Polynomial Degree Selection
Machine Learning
The K-fold cross-validation simulator fits polynomials to 1D data and picks the best degree by K-fold CV. Compare train MSE and CV MSE to see when overfitting starts.
k-Means Clustering Simulator
Machine Learning
Run the classic unsupervised-learning algorithm k-means (Lloyd's algorithm) and watch it work.
k-NN 2D Classifier Simulator — Decision Boundary and LOO Accuracy
Machine Learning
Visualize a k-NN classifier on three-class 2D training data. Change k, the query point and the data spread to learn how the decision boundary and the LOO accuracy respon…
Kriging Surrogate Model (Gaussian Process Regression) Simulator
Machine Learning
Replace expensive CFD/FEM evaluations with a Kriging (Gaussian Process Regression) surrogate built from just a few training points.
Learning Curve Simulator — Diagnose Overfitting & Underfitting
Machine Learning
Diagnose whether a machine-learning model is overfitting or underfitting using the learning curve — the training error and validation error plotted against the amount of…
Learning Rate Schedule Simulator
Machine Learning
Visualize the learning rate schedules used to train neural networks.
Linear SVM Simulator — Soft-Margin 2D Classification
Machine Learning
Train a linear SVM on 2D data via subgradient descent. Visualize the maximum-margin hyperplane, support vectors and the hinge-vs-L2 tradeoff controlled by C.
Logistic Regression (2D Binary Classifier) Simulator
Machine Learning
Minimize cross-entropy loss with gradient descent on a sigmoid model. Change the learning rate, iterations and L2 regularization to see how the linear decision boundary …
Gaussian Naive Bayes Classifier Simulator — 2D, 3 Classes
Machine Learning
Visualize log-posteriors and decision boundaries of a 2D, three-class Gaussian Naive Bayes classifier. Move the query point, shift sigma and resample to see the effect.
Neural Network Visualizer — Forward & Backpropagation in Real Time
Machine Learning
Visualize and train neural networks in real time. Learn how forward propagation and backpropagation solve the XOR problem with interactive examples.
Principal Component Analysis (PCA) Simulator — Eigendecomposition for 2D Data
Machine Learning
Visualize PCA on correlated 2D data in real time. Eigendecomposition of the 2x2 covariance matrix yields principal axes and explained variance ratios.
Perceptron Learning Simulator — Linear Classifier Convergence
Machine Learning
Visualize the learning rule of a 2-input single-layer perceptron y = sign(w1 x1 + w2 x2 + b). Watch how the decision boundary converges on linearly separable data while …
Policy Gradient Simulator
Machine Learning
Experience REINFORCE, a classic reinforcement-learning algorithm. On a continuous-action task, watch the mean of a Gaussian policy slide toward the optimal action and se…
Pooling Layer Simulator — CNN
Machine Learning
Explore the pooling layer of a CNN (convolutional neural network).
Q-Learning Simulator — Reinforcement Learning Gridworld
Machine Learning
Run Q-learning, the foundation of reinforcement learning, in a maze-like gridworld. Adjust the learning rate, discount factor and exploration rate, and watch in real tim…
Random Forest Majority Vote — Bagging and Variance Reduction
Machine Learning
Train T decision trees with bootstrap sampling and feature subsampling, then predict by majority vote. Compare a single tree against the ensemble and see why aggregation…
L1/L2 Regularization Simulator — Lasso vs Ridge
Machine Learning
Visualize the behavior of the two regularizers that fight overfitting in machine learning: L1 (Lasso) and L2 (Ridge).
Softmax and Cross-Entropy Loss — Core of Classification
Machine Learning
The Softmax and cross-entropy loss simulator turns three-class logits and a temperature parameter into a probability distribution and loss value in real time.
Spectral Clustering Simulator
Machine Learning
Treat pairwise affinities as a graph, take the leading k eigenvectors of the normalised Laplacian L=D^-1/2(D-W)D^-1/2, and run k-means in that embedded space. Watch spec…
Stochastic Gradient Langevin Dynamics (SGLD) Simulator
Machine Learning
SGLD (Welling & Teh 2011) turns a stochastic-gradient optimiser into a Bayesian posterior sampler by adding a sqrt(2η) Brownian kick at every step.
TF-IDF Vectorizer Simulator
Machine Learning
Explore TF-IDF, the classic recipe for turning text into numeric vectors a machine-learning model can use.
Transformer Attention Basics Simulator
Machine Learning
Experience scaled dot-product attention, the heart of the Transformer, with just three tokens.
Weight Initialization Simulator — Xavier & He
Machine Learning
Visualize how the activation variance evolves as an input signal forward-propagates through a deep neural network. Switch the initialization scheme and see at a glance w…

How to Use

  1. Select your dataset category using the cat-filter dropdown (classification, regression, clustering, or NLP)
  2. Input your training parameters: learning rate (0.001–0.1), batch size (16–512), and epoch count (10–500)
  3. Configure model hyperparameters (hidden layer neurons, activation functions, regularization lambda 0.0–0.01), then execute simulation to observe convergence metrics and loss curves

Worked Example

Binary classification on a 1000-sample medical dataset: logistic regression with learning rate=0.01, batch size=32, epochs=100, L2 regularization lambda=0.005. After 87 epochs, training loss converges to 0.124, validation accuracy reaches 94.2%, and test F1-score = 0.916. Increasing lambda to 0.01 reduces overfitting gap from 3.8% to 1.2% but final accuracy drops to 93.1%, illustrating bias-variance tradeoff in pharmaceutical diagnostics screening.

Practical Notes

  1. For imbalanced classification (e.g., fraud detection with 2% positive class), adjust class weights inversely; simulator applies 50:1 weighting automatically when detected
  2. Gradient descent oscillation near minima indicates learning rate too high; reduce by 50% and rerun to stabilize convergence in regression tasks
  3. Batch sizes below 16 introduce high noise in neural networks; sizes above 256 reduce memory efficiency without accuracy gains on datasets under 100k samples