Modern Deep Learning Foundations
Your six-laboratory learning path
AUC-ROC Evaluation
Inspect the confusion matrix, move the classification threshold, and connect precision, recall, F1, ROC, and AUC on one consistent dataset.
Open simulator
Generalization and Regularization
Compare training and validation behaviour while model capacity, regularization strength, and data conditions change.
Open simulator
CNN Lab
Explore a complete CNN pipeline with real benchmark samples, editable kernels, padding, stride, pooling, and layer-level activations.
Open simulator
Self-Attention Lab
Trace token embeddings through Query, Key, Value projections, scaled dot-product attention, multi-head mixing, and residual updates.
Open simulator
Explainability Lab
Compare local feature attribution methods and inspect how evidence supports or opposes a model prediction.
Open simulator
Transfer Learning Lab
Freeze and unfreeze a pretrained network block by block, then observe trainable parameters, adaptation, expected accuracy, and forgetting risk.
Open simulator