🧵Deep learning simulation of brain activity

Just like self-driving cars, BCIs are control systems. High-fidelity simulations of motor cortex activity can speed up evaluation of neural decoders and enable optimization methods like reinforcement learning.

Using our brain simulator, we’ve trained a reinforcement learning agent to maximize bits per second. Here is the RL policy converting brain data to cursor control in simulation:

High performance in simulation is exciting, but what happens when we deploy this neural decoding policy in the real world? If our simulation is accurate, users should achieve similar performance in real-world applications.

We’re in the early stages of generative brain modeling, but Pager can already use decoders trained in simulation to acquire targets in the real world:

holds the BPS world record of 9.5 bits per second (bps). The challenge now: can this approach scale to 10 bps and beyond for our participants?

If you want to answer this question, apply here:

Can you guys figure out how to grow my penis

This is cool, now imagine what it would look like with a Whole Brain Interface? I'm excited for the future (2030s 🤞) Also, check out my Neurotech/BCI & VR community for BCI updates and news

Confused about AI? Get clarity today with Book VI - "The Rational Being!" Understand the benefits & risks, empower your future now by learning what AI really is and how it really works! Also check out the Free Weekly Newsletter "How Things Work: A Brief History of Reality"

I’m not sure my brain has a whole lot of activity.

Interesting