PerceptionTime VS distributAr

I would like to disagree. Spikes have everything to do with intelliegence. Perception to be exact. Here are my arguments: https://github.com/rand3289/PerceptionTime

Over the next five years I kept thinking about a theory that would not use symbols during computation. Came up with some arguments but they weren't convincing enough. Now I live in my own world. All I got is this Idea that's not even an architecture but explanation why spiking NNs is the way to go: https://github.com/rand3289/PerceptionTime

Qualia can not be expressed symbolically. I have a theory that qualia can be expressed as a point in time though. A spike. This point in time is "formed" when an agent detected a change within itself. The change was caused by its environment. Here is more info: https://github.com/rand3289/PerceptionTime

I would argue that spikes are points in time and are NOT symbolic in nature. They can be expressed as symbols (timestamps) however. Here is more info: https://github.com/rand3289/PerceptionTime

Perception becomes subjective when there is a body. Here is more info: https://github.com/rand3289/PerceptionTime

I completely agree! This is how I belive we can bring time into the model of consciousness: https://github.com/rand3289/PerceptionTime

Here are some of my own ideas: https://github.com/rand3289/PerceptionTime

Here is the source: https://github.com/rand3289/distributAr

Software (AI) is the limiting factor. This is how I am working on that: https://github.com/rand3289/distributAr https://github.com/rand3289/PerceptionTime

And here is my framework for distributing spikes in a private IPv4 network: https://github.com/rand3289/distributAr

#1: My tiny (2.5k lines of C++ code) framework for distributing SPIKING neural networks. | 0 comments #2: Introducing Pathways: A next-generation AI architecture | 0 comments #3: Neuron Bursts Can Mimic Famous AI Learning Strategy | 0 comments

I have a tiny (under 2000 lines of C++) opensource framework for distributing spiking ANNs. It could easily be adapted for other purposes. One distinguishing features is it has time synchronization among the nodes build in. Nodes can be connected manually or by drawing a graph and uploading it into the network. All you have to provide is a DLL that performs the actual computation and implements read() and write() methods. I hope this will be useful for someone. https://github.com/rand3289/distributAr

Do you have anything on paper? Any ideas? Surely you have something??? For example here is my framework for distributing spiking ANNs: https://github.com/rand3289/distributAr

I noticed some similarity in what we are both working on. Although I do not have an algorithm, I have a "theory", a framework for distributing spikes (similar to your "architecture") and just like you, I am working on inexpensive sensor and actuator frameworks. I am not working on social or safety problems though... Here is the framework for distributing spikes: https://github.com/rand3289/distributAr The other things I've described are in the links in my earlier comments. I am a bit concerned about the fact you are not making implementation public. I hope you realize that Elon Musk created a company specifically for the purpose of sharing the technology so that no single entity posses it. My paper is really simple! I am stating that things that are alive process information by detecting changes in their internal state. Internal state can be meat or bits. It just happens that "detecting internal state change" is best described by a point in time (a timestamp or a spike). I call it a "perception mechanism" but it describes both sensory and non-sensory neurons.