Matrices
Matrices represent linear maps and batches of vectors throughout neural-network computation. Matrix multiplication composes learned projections, but nonlinearities are required for deep networks to express nonlinear functions.
Y=XW+b
Overview. Matrices represent linear maps and batches of vectors throughout neural-network computation.
Context. Matrix multiplication composes learned projections, but nonlinearities are required for deep networks to express nonlinear functions.
Claims and evidence
Claim ledger, 2Matrices represent linear maps and batches of vectors throughout neural-network computation.
Matrix multiplication composes learned projections, but nonlinearities are required for deep networks to express nonlinear functions.