3 papers
cs.ET2024
The Physics of Learning: From Autoencoders to Truly Autonomous Learning Machines
Alex Ushveridze
The fact that accurately predicted information can serve as an energy source paves the way for new approaches to autonomous learning. The energy derived from a sequence of successf…
cs.AI2024
Understanding Learning through the Lens of Dynamical Invariants
Alex Ushveridze
This paper proposes a novel perspective on learning, positing it as the pursuit of dynamical invariants -- data combinations that remain constant or exhibit minimal change over tim…
q-bio.NC2023
On Physical Origins of Learning
Alex Ushveridze
The quest to comprehend the origins of intelligence raises intriguing questions about the evolution of learning abilities in natural systems. Why do living organisms possess an inh…