Three accepted papers, one architecture proven at scale

A Uniform, Tessellated Architecture for Energy-Efficient Learning and Inference

Presents the foundational Brain-CA architecture as a scalable grid of identical cells that learn through wave collisions and spatial patterns. The focus is on how intelligence can emerge from simple, geometric interactions — replacing central control and complex math with distributed logic.

Brain-CA: A Dual-Speed, Low-Energy Architecture for Cognitive Learning via Cellular Automata

Introduces a biologically inspired dual-speed system that separates slow wave-based learning from fast path-based prediction. Highlights how randomness and binary modeling enable the system to adapt and reason like a cognitive agent — with minimal energy and no layered neural networks.

Brain-CA: A Cellular Automata-Inspired Architecture for Energy-Efficient CPU Design

Reimagines the CPU itself using Brain-CA’s event-driven, decentralized architecture. Focuses on replacing traditional instruction-based processing with lightweight, embedded learning elements to drastically reduce energy consumption in data centers and general-purpose computing.