continual learning neolab
Miruvor is a deep-tech AI research lab building brain-inspired continual learning models. Spiking neural networks, local learning rules, neuromorphic silicon.
For years, the field converged on a single equation: pretrainingdatacomputeintelligence It produced remarkable results. But the systems it produced have no persistent state. They do not learn from experience after training ends. Every inference begins from zero. The architecture has no mechanism for it. We have hit a wall. To reach new frontiers of intelligence, true continual learning, persistent memory, real-time adaptation, we need better representations, better efficiency, and a new architecture. Miruvor is building that architecture. We are a deep-tech AI research lab developing a…
saved by
related reading
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- AI 2027ai-2027.com
- MoNETA: A Mind Made from Memristors - IEEE Spectrumspectrum.ieee.org
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- NL.pdfabehrouz.github.io
- The Continual Learning Problemjessylin.com
- Cortical Labscorticallabs.com
- Challenges of governing continually learning AIruntimeverification.blog
- Loss of plasticity in deep continual learning | Naturenature.com
- Supermemory — Memory and continual learning for agentssupermemory.ai
- AI 2027ai-2027.com
- Continuous Thought Machinespub.sakana.ai