Dave
4.5K posts


A Neural Network Can Grow New Neurons Where It Is Confused? In 1994, Bernd Fritzke published A Growing Neural Gas Network Learns Topologies. He introduced a network that starts small, follows incoming data, and inserts new neurons where its error is highest. In the animation, the fog is the drifting data. The glowing nodes are neurons. The fibers are learned connections. The network grows into a living skeleton of the manifold.



You guys aren't going to believe this (I had to double check it was real). Unitree has made an actual mecha like Gundam, the GD01.


I built whichhumanoid.ai, the world's first buyer's directory for humanoid robots. Tesla Optimus, Figure 02, 1X Neo, Unitree R1, AgiBot, Apptronik Apollo. Every robot side-by-side. Compare any two like you'd compare two cars. What's inside: → 308 humanoid robots catalogued → Compare on price, payload, height, walking speed, and funding → Filter by use case (manufacturing, home, healthcare, defense) → Live ticker of every shipment, launch, and customer deploy → Submit any humanoid I missed A few things that surprised me building it: → Only 66 of 308 are shipping today → Only 32 publish a price → Only 30 have a verified customer deploy → Cheapest shipping robot is Unitree R1 at $4,900. The highest price I've seen is $250,000. P.S. Find a bug, DM me. I'll fix it same day.


This video is going viral on Instagram. The first fight ever between an Engine and Unitree robot at our new store space in SF.

















