Concepts2

Groups

E(n) Equivariant Neural Networks

E(n)-equivariant neural networks are models whose outputs transform predictably when inputs are rotated, translated, or reflected in n-dimensional Euclidean space.

#e(n)-equivariance#euclidean group#so(n) and o(n)+12

📚TheoryIntermediate

Positional Encoding Theory

Transformers are permutation-invariant by default, so they need positional encodings to understand word order in sequences.

#positional encoding