ideasthesia

Sign in Subscribe

Ryan Collison

I write about cool science and share it here.

Synthesis of hyperdimensional computing and biological coherence

Synthesis: What Hyperdimensional Computing Teaches About Efficient Coherence

Series: Hyperdimensional Computing | Part: 9 of 9 The question isn’t whether biological systems compute. It’s how they manage to do it so efficiently—with minimal energy, no training cycles, and graceful degradation under noise—while our best silicon implementations burn through kilowatts and collapse under edge cases. Hyperdimensional

Active inference implemented through hyperdimensional computing

Where Hyperdimensional Meets Active Inference: Efficient Coherence Computation

Series: Hyperdimensional Computing | Part: 8 of 9 What if the computational architecture that makes your brain efficient at prediction is the same architecture that makes hyperdimensional computing work? This isn’t just theoretical convergence. The mathematics of high-dimensional vector spaces might explain how biological systems implement active inference without

Cognitive architecture built on hyperdimensional computing

Hyperdimensional Computing for Cognitive Architectures

Series: Hyperdimensional Computing | Part: 7 of 9 In 1956, the first summer conference on artificial intelligence at Dartmouth launched a field based on a single working hypothesis: intelligence is symbol manipulation. Build the right data structures, implement the right algorithms, and cognition would emerge. Sixty-eight years later, we have

Semiconductor chips designed for hyperdimensional computing

Intel and IBM Bet on Hyperdimensional: Industry Applications

Series: Hyperdimensional Computing | Part: 6 of 9 When Intel shut down its neuromorphic computing research division in 2021, the tech press barely noticed. When they restarted it six months later with expanded funding, even fewer people paid attention. But something happened in that quiet interval: Intel’s engineers ran the

Edge device running hyperdimensional computing efficiently

Hyperdimensional Computing Beats Transformers (On Edge Devices)

Series: Hyperdimensional Computing | Part: 5 of 9 Your smartwatch doesn’t run GPT-4. Your doorbell camera can’t load a transformer. Your wireless earbuds would melt trying to compute attention mechanisms. And yet—they need to recognize your voice, detect motion patterns, classify sounds. The AI revolution promised intelligence

High-dimensional geometric space with surprising properties

Why High Dimensions Are Magic: The Geometry of Hypervectors

Series: Hyperdimensional Computing | Part: 4 of 9 Most of us learned geometry in three dimensions—maybe four if your physics teacher was feeling ambitious. So when someone tells you that the interesting stuff happens in 10,000 dimensions, your brain reasonably protests. How could adding more dimensions make anything easier?

Hypervector operations binding and bundling in high-dimensional space

The Algebra of Hypervectors: Binding, Bundling, and Permutation

Series: Hyperdimensional Computing | Part: 3 of 9 The most profound computational architectures often hide in plain sight. For decades, we’ve watched neural networks dominate machine learning while a radically different approach—one that operates in dimensions so high they defy geometric intuition—has been quietly demonstrating how brains might