Dataset

Upload CSV or Excel with a target column

Try with a sample dataset

Pick one to explore instantly — no upload needed

Architecture

MLP

Hidden layer configuration

Hidden Layers

Network: Input → 100 → Output

Activation Function

Most popular choice. Fast training, avoids vanishing gradients. Default for most tasks.

Optimizer

Recommended for most cases. Adapts learning rates per parameter. Works well with large datasets.

Training

Optimization hyperparameters

Alpha (L2 Penalty)10^-4

Less regularization (10⁻⁸)More regularization (10⁰)

L2 penalty term. Larger values prevent overfitting by constraining weights.

Learning Rate10^-3

Slower (10⁻⁵)Faster (10⁻¹)

Max Iterations200

Quick (50)Thorough (1000)

Batch Size

Early Stopping

Stop training when validation score stops improving

Train / Test Split

Holdout proportion for evaluation

Test Size20%

Train: 80%Test: 20%

Preprocessing

Feature transformations

Enable preprocessing

Advanced settings

Projection

2D visualization method

PCA for quick linear projection. UMAP for complex manifolds.

Parameter Guide

Click to expand

Performance Metrics

Accuracy

—

Awaiting training

Precision

—

Awaiting training

Recall

—

Awaiting training

F1 Score

—

Awaiting training

ROC AUC

—

Awaiting training

Dataset

—

Awaiting training

Classification Visualization

Classification Results

Interactive scatter plot of classification results

Run training to render the scatter plot

Advanced Analysis

Deep Dive Analysis

Run training or prediction to populate analysis

Run training or prediction to see results here.

Job History

Recent jobs — auto-pruned to keep 10 per type

No jobs recorded yet. Run a clustering, classification, or pipeline job to see results here.

Loading…

Dataset

Upload CSV or Excel with a target column

Try with a sample dataset

Pick one to explore instantly — no upload needed

Architecture

MLP

Hidden layer configuration

Hidden Layers

Network: Input → 100 → Output

Activation Function

Most popular choice. Fast training, avoids vanishing gradients. Default for most tasks.

Optimizer

Recommended for most cases. Adapts learning rates per parameter. Works well with large datasets.

Training

Optimization hyperparameters

Alpha (L2 Penalty)10^-4

Less regularization (10⁻⁸)More regularization (10⁰)

L2 penalty term. Larger values prevent overfitting by constraining weights.

Learning Rate10^-3

Slower (10⁻⁵)Faster (10⁻¹)

Max Iterations200

Quick (50)Thorough (1000)

Batch Size

Early Stopping

Stop training when validation score stops improving

Train / Test Split

Holdout proportion for evaluation

Test Size20%

Train: 80%Test: 20%

Preprocessing

Feature transformations

Enable preprocessing

Advanced settings

Projection

2D visualization method

PCA for quick linear projection. UMAP for complex manifolds.

Parameter Guide

Click to expand

Performance Metrics

Accuracy

—

Awaiting training

Precision

—

Awaiting training

Recall

—

Awaiting training

F1 Score

—

Awaiting training

ROC AUC

—

Awaiting training

Dataset

—

Awaiting training

Classification Visualization

Classification Results

Interactive scatter plot of classification results

Run training to render the scatter plot

Advanced Analysis

Deep Dive Analysis

Run training or prediction to populate analysis

Run training or prediction to see results here.

Job History

Recent jobs — auto-pruned to keep 10 per type

No jobs recorded yet. Run a clustering, classification, or pipeline job to see results here.

MLP Neural Network Classifier — Interactive Analysis