no code implementations • 11 Dec 2024 • Jaesung R. Park, Jaewook J. Suh, Ernest K. Ryu
In deep learning, the recently introduced state space models utilize HiPPO (High-order Polynomial Projection Operators) memory units to approximate continuous-time trajectories of input functions using ordinary differential equations (ODEs), and these techniques have shown empirical success in capturing long-range dependencies in long input sequences.
1 code implementation • 4 Nov 2024 • Stephen P. Boyd, Tetiana Parshakova, Ernest K. Ryu, Jaewook J. Suh
We present a novel methodology for convex optimization algorithm design using ideas from electric RLC circuits.