ArtificialGate interactive laboratories

Modern Deep Learning Foundation Playground

Six focused, browser-based laboratories for the concepts that benefit most from direct experimentation. Every laboratory now has its own full page, stable workspace, and focused learning objective.

Modern Deep Learning Foundation by Dr. Barak Or
Focused curriculum

Six complete learning laboratories

05 Interactive lab

Performance Evaluation Metrics

Inspect the confusion matrix, move the classification threshold, and connect precision, recall, F1, ROC, and AUC on one consistent dataset.

  • Confusion matrix
  • Threshold analysis
  • ROC and AUC
Open laboratory
06 Interactive lab

Overfitting and Regularization

Compare training and validation behaviour while model capacity, regularization strength, and data conditions change.

  • Bias and variance
  • Regularization
  • Generalization gap
Open laboratory
08 Interactive lab

How Does a CNN Work?

Explore a complete CNN pipeline with real benchmark samples, editable kernels, padding, stride, pooling, and layer-level activations.

  • MNIST and CIFAR-10
  • Activations and pooling
  • Tensor shapes
Open laboratory
11 Interactive lab

Self-Attention and the Transformer Principle

Trace token embeddings through Query, Key, Value projections, scaled dot-product attention, multi-head mixing, and residual updates.

  • Q, K, and V
  • Multi-head attention
  • Residual stream
Open laboratory
15 Interactive lab

Explainability: Understanding Model Decisions

Compare local feature attribution methods and inspect how evidence supports or opposes a model prediction.

  • Feature attribution
  • Local explanations
  • Explanation stability
Open laboratory
19 Interactive lab

Transfer Learning and Fine-Tuning

Freeze and unfreeze a pretrained network block by block, then observe trainable parameters, adaptation, expected accuracy, and forgetting risk.

  • Frozen layers
  • Partial fine-tuning
  • Catastrophic forgetting
Open laboratory