Ben Hoover
@bhoov.bsky.social
PhD student@GA Tech; Research Engineer @IBM Research. Thinking about Associative Memory, Hopfield Networks, and AI.
MrDAM energies can be decomposed into:
1️⃣A similarity func between stored patterns & noisy input
2️⃣A rapidly growing separation func (e.g., exponential)
Together, they reveal kernels (e.g., RBF) that can be approximated via the kernel trick & random features (Rahimi&Recht, 2007)
1️⃣A similarity func between stored patterns & noisy input
2️⃣A rapidly growing separation func (e.g., exponential)
Together, they reveal kernels (e.g., RBF) that can be approximated via the kernel trick & random features (Rahimi&Recht, 2007)
December 3, 2024 at 4:33 PM
MrDAM energies can be decomposed into:
1️⃣A similarity func between stored patterns & noisy input
2️⃣A rapidly growing separation func (e.g., exponential)
Together, they reveal kernels (e.g., RBF) that can be approximated via the kernel trick & random features (Rahimi&Recht, 2007)
1️⃣A similarity func between stored patterns & noisy input
2️⃣A rapidly growing separation func (e.g., exponential)
Together, they reveal kernels (e.g., RBF) that can be approximated via the kernel trick & random features (Rahimi&Recht, 2007)
Excited to share "Dense Associative Memory through the Lens of Random Features" accepted to #neurips2024🎉
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
December 3, 2024 at 4:33 PM
Excited to share "Dense Associative Memory through the Lens of Random Features" accepted to #neurips2024🎉
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓