Conclusion
- There are five things I'd like you to take home.
- You can program in neurons.
- Neurons are not currently winning vs. standard text engineering
approaches.
- Neurons are, of course, winning as neuro-cognitive models.
- Neurons are starting to win as cognitive models.
- Neurons hold the promise of unifying disparate systems; this could
solve the symbol grounding problem and lead to a Turing test
pasing agent.
- It's hard to develop systems with neurons, but there are an incredibly
wide amount of things to study and ways to make advances.
- I can't think of a better way to pass the Turing test.
- Cognitive and hard AI claims aside, there is promise from a text
engineering perspective for neurons.
