ACADEMIC WORK & TECHNICAL EXPLORATIONS
Exploring how
machines learn.
Architecture, data, optimization, and the questions in between. A collection of academic studies with interactive explanations and room for the experiments to come.
4 ACADEMIC STUDIES
ARCHITECTURE STUDYFNN / CNN
Local patterns. Different inductive biases.
FNN vs CNN
Exploring how architectural inductive biases shape learning on a sequence-based latch task.
DIMENSIONALITY REDUCTION3D → 2D
Synthetic-data projection
Seeing data differently
From high-dimensional features to interpretable projections with principal component analysis.
UNSUPERVISED LEARNINGHIERARCHICAL
Illustrative dendrogram
Finding structure without labels
Investigating hierarchical clustering, distance metrics, and the structure hidden in unlabeled data.
ARCHITECTURE STUDYFNN / CNN
Local patterns. Different inductive biases.
Inside the training loop
Connecting neurons, gradients, and parameter updates to the mechanics of learning.