Dev Blog

• the system
• work to understand people
  • understand why they do what they do
  • understand what is their motivation
  • understand something that is happening and the person's motivation to make such an event happen.
• determine if the event will cause harm to others
  • cost benefit analysis
• identify perpetrator
• identify victims
• identify person in the position to help the most
  • notify person

• papers titled “A Model for Self-Organization of Sensorimotor Function: The Spinal Monosynaptic Loop“ and “Spinal Intraneuronal Integration”
• self organization of spinal circuitry

• They are not Spikes, they are sparks.
• in terms of self assembling structures
• and spiking neural networks
• they're not spikes, their sparks as in lightning
• the electricity builds up and then discharges.

• along with self assembling structures
• Battery dendrite formation
• Simulating dendrite formation

• self assembling stuctures
• youtube video self-assebmling wires
• Dr. Hubler
• This behavior solves the node connection problem

• I first tried to figure out gravity. I.e. create anti-gravity
• I didn't have much understanding of electronics or physics at the time and didn't have path forward in solving such a problem
• Then I wasted some time trying to figure out infinite energy. Had some ideas but these were quickly tested by others and shown not to be a useful solution.
• I then got a job doing natural language processing, which is machine learning or Artificial intelligence.
• Once I started grasping this world, it all coalesced.
• I've been studying human behavior, i.e. psychology, because I don't understand people
• But I've also been studying computer programming.
• When you merge these 2 together, you get Artificial Intelligence.
• And I started thinking about how the human brain works and how someone could recreate the human brain in a computer.
• I had an idea on how to solve this.
• I spent the next 15 years trying to determine an algorithm that would recreate this behavior
• in 2015, I realized exactly what algorithm would behave like the human brain.
• Since 2015, I started trying to figure out how to fund the effort of taking this algorithm and turning it into a full product.
• at the end of 2020, I succeeded in creating the funds needed to pursue this algorithm full time.
• Now, I have been thinking about how this algorithm could help people.
• It can be used to automate production.
• It could be used to subvert the governments of the world and make societies better for the common person.
• It could be used to generate even more money, but if it automates the means of production, money would be meaningless.

Inner monologue

• A normal(25% of people) person will have both and inner dialog with their logical brain and with their emotional brain.
• A person with Asperger's only has an inner dialog of their logical brain.
• apparently there are people with only the emotional dialog, probably highly empathetic people.

• Do you have an emotional inner dialog?
• Do you have a logical inner dialog?
• Do you have both that argue with each other?
• Do you have neither, and only feel emotions?

Dynamic population encoding algorithm author : Tofara Moyo We believe that humans map inputs to actions. In order to do this optimally some action in the distant past has to have an effect on the present actions. This was handled by nature by giving some means to divert the input signal and have the diverted signal influence the action at a later stage. This was also sufficient to make this a function, because similar states could now cause widely different actions because the action was conditioned not only on the current state, but also on the diverted input signal. Also, within the brain, which was made with the sole purpose of diverting the signal, subnetworks with strong local connectivity within themselves would cause different effects to other networks (even those with other networks in between) at different times by diverting the signal they received, through the rest of the networks, before affecting the network they were trying to effect. This is true pairwise between every network in the brain. The neural model we propose consists of a networked cellular automaton, where unlike in a traditional cellular automaton where physical boundaries determine neighbours, neighbouring cells could be “further” apart. What this means is that it will be necessary to keep an adjacency matrix that shows which neurons are connected to which. The network will be initialized randomly with 2 % connectivity throughout the network in order to simulate sparse codes.Then spectral graph analysis will be used to determine which segments the network can be broken into most logically. An agent A will be assigned to each subnetwork, and its set of actions will have it move from node to node within its subnet . We borrow ideas from internetworking by having an instance of the rapid spanning tree protocol running in each network. The rapid spanning tree algorithm is used in cisco routers in order to prevent loops within a network. It does so by determining which connections should be blocked and which maintained. we will use the RSTA in order to adjust the topology of each of the subnetworks. Within RSTA switches exchange information in order to vote for a root bridge/switch. The choice of root bridge finally settled on influences how the topology of the network will be set. In our case we will omit the voting feature from our implementation. instead the node that the agent A associated with the subnetwork is currently positioned on will be chosen as the root node. Note that the agent A is free to hop from node to node, even if they are not directly connected. Once the root node is chosen , the topology of the subnet is adjusted in line with this information. Our aim is to get each agent A to maximise its own reward by indirectly changing the topology of the network and influencing yet another network, which will act as the environment of the agent. Each agent A will be associated with two networks. the network that it is hoping from node to node in, and one of the other networks. This secondary network will act as a part of the environment for the agent and will give it its reward. In a robotic system, once the total reward is calculated we would like a way to use it to influence which rewards a particular network feeds its paired agent A. this will be done by having each network keep a Q table with the action being increasing or decreasing the reward that the network gives out and the state being the global reward. This means in short that each network has two associated agents, A and B. One A that hops from node to node changing the topology of the network. And one B that calculates the reward it should emit to the diametrically opposed agent from the paired network. The dynamics of the network would have each network’s agent A figure out a way to maximise its total personal reward by changing the topology of its network, and causing a ripple effect that will modulate the network that is diametrically opposite it. This reward is calculated by the second network's agent B from the global reward. This second agent maximises (its) the global reward, by giving the first agent the most fitting rewards for actions. In order to connect this to traditional neural networks we will do the following. Given the input to the neural network we will have the outputs of this network be given a multi class distribution where the input activates some of the cells in a particular network within the neural model. One of the other networks in the model will act as a teacher and have mirrored neurons for each of the output neurons mentioned. Once the neural network has received some input and predicted the particular cells that it does. The difference between the signal received by the mirrored neurons and the neural networks output cells will be used to come up with a loss value in which to train the neural networks.

• It creates multiple connections then drops around 30% of those connections : ref - Workshop on continual learning | CVPR 2020 | subutai ahmad

• Input - Paper about sensors in the eye
• Node creation - paper about neuro plasticity
• Output Discovery - My own work in watching the neuron algorithm
• Feedback loop - paper about sine wave behavior in the brain

• Brain like behavior nanoscale device

• another potential market - Building control

• what if I track node activation with reward output feedback, where it sees the nodes that contributed to the result and it works to minimized the path between the input nodes and the output nodes.

• desire is to connect to an output. I.e. if there isn't a output that is stimulated then trying to find that connection is the driving force. “Something is nagging me and I can't quite put my finger on it.”

• am I driving the nervous system or am I remembering the sensation of the memory system?

• Multiple inputs drive intensity of neuron activation. The intensity competes with other stimulus. The one with the most intense activation drives motors. If none are intense enough then they just linger as thoughts.
• is the spinal cord more of an input/output without intensity? The brain is more about thought which gives suggestions to the spinal cord? muffling the input/output of the brain?
• I think it is the complexity of inputs. There are so many inputs and outputs that the brain can linger on a thought without activation because the combined intensity is still low enough not to activate the motor.

• I have to continue living the life that I have been living to make progress on TrueAI. Without this interaction or activities that I experience, I will not be able to make breakthroughs on how people work. For example. I'm currently watching servamp anime. Which gave me insight into sadness and how the physical body reacts to that emotion and how those reactions drive the mind. All of this, through the way I live.

• Persistence of neuronal representations through time and damage in the hippocampus.

This paper describes pretty accurately how my algorithm works. and based on it's description you can correlate what my algorithm is doing to the behavior that they describe.

Had a discussion with a person from DARPA. She said a lot of interesting things. Most notably, I need to formalize my work into scientific papers. Yes, multiple. I would need to start from existing research and show how I got to where I am.

here are notes from the meeting

open baa
hp1 - contract type
hebbian learning 
neurons fire together fire together
aie - contract type
white paper -- problem space - class of problems - metrics - 
portfolios on polyplexus - abstract

• arm lightweight cores cpu

• Ok, so there is the thing called Spiking Neural Network. From the high level description, it sounds really close to what I have built.
• But the earliest paper I could find is 2002. How have they not created a fully functional human level intelligence by now?
• here's a paper - Spiking Neural Networks - The Next Generation of Machine Learning
• It's just a variation on neural networks.
• link weights → delay activation
• sigmoid → accumulation of spikes
• layers and nodes are still there along with everything is connected to everything (from one layer to the next) and the flow through the graph is controlled by link weights
• they have multiple discrete networks that are connected by a routing function
• basically it's an efficient implementation of a neural network in silicon.
• So they are able to create very large networks that compute really fast and don't use a lot of electricity

• The heat map of the link weights on a neural network shows how the network is inflexable if the data gets to disparate.
• Heat Map

• Stroke victim retains hand
• Chess Games
• Cortical Layers
• Girl Sees Fine With Half a Brain
• Neuronal networks and synaptic plasticity: understanding complex system dynamics by interfacing neurons with silicon technologies
• The Mechanism that Controls the Direction of Axon Elongation
• Neuron Silicon Interface

• they are looking at a car and they are looking at the materials that make up the car but they don't even have a concept of what a bolt is and how it plays within the system of making a car.
• The hippocampus as a predictive map
• This neuroscience paper has a better understanding of how the brain works.

Neural networks have reached their peak. It's evident by looking at how they architected Alpha Star. Alpha Star uses a very cluegy architecture to solve the problem. It's not self contained within a neural network. Also, the errors that happen within a neural network, don't happen within a human brain. My algorithm is elegant. It's simple. You have 2 nerve ends and they are active. The brain says, connect those 2 with a neuron. Then you have 2 active neurons. the brain says, connect those 2. and so on. This is played out in the real world. Scientists conducted a test where they put a brain slice on a silicon chip. The brain slice grew to where there was activity on the silicon. It is a very simple process that is capable of very complex action and I've captured it within my algorithm.

Maybe I should study psychology

• Seeking Comfort the impossible way, Emotions motivate us to do something
• Theory of Consciousness, self model

With the input nodes “growing” to connect the the same kind of “growth” for the output nodes. This mid line connection is what creates consciousness. When training the output side has an active node tree. But after learning a few inputs the mid line will have more than one active node. This multiple activation is what gives rise to humans pondering what action to take.

This and also the before mentioned, constant looping of the thoughts which give rise to active memory.

• maybe of interest
• https://aws.amazon.com/deepracer/
• https://hackaday.com/2018/11/30/buy-or-build-an-autonomous-race-car-to-take-the-checkered-flag/

• From the top layer from the input nodes.
• Connect to the output node
• if there are more than one node active at the top of input nodes, create a new node connecting them
• If there is a layer above the top nodes, for all that are active create a new layer along with a new node
• there needs to be a layer with only one node active to connect to the output node.
• but just like with the input layers, they are capped to 7 layers

• activation is just the individual nodes cascading the chain to the output nodes. Easy to make parallel
• This activation needs to be stored then recalled later for training, short term memory
• training is a slow linear process. i.e. dreams

• applying to investors, below is a list of ones that I've applied.
• https://fundersclub.com/
• http://innovationplatformcapital.com/
• https://www.seedequity.com/
• https://www.ourcrowd.com/

• angel investors - https://www.inc.com/guides/start_biz/24011.html

• https://www.angelcapitalassociation.org/directory/

• So I realized out to output from the network
• just work backwards from the primary active node down to the desired output node

• Multiple relationships of patterns that represent clusters.
• It's a multi-relationship database of patterns

• http://www.ros.org/ Start wiht this to simulate the ai controlling a robot.

• Google Search funding

• the difference between my A.i. and neural networks
• neural networks are not able to have disparate conflicting ideas
• for example: the dataset has zeros for inputs 1-10 and values for 11-15
• these inputs conclude a certain output
• then you have values for 1-5 but zeros for 6-15
• these new set of values are pointing to a different output or the same one
• neural networks cannot handle this.

• Background video that pre-dates the “Body & Mind” video
• I have aspberger's
• Pay a lot of attention to how/why people do things
• TLC had various shows on about how the mind works
• Self understanding with the mirror concept
• Heart attack/stroke but still able to relearn, shows new path ways neurons being formed
• Reaction time, showing an MRI scan that shows the inception point of a thought
• Talk to an MRI scan between Aspberger's and a normal person
• Not a focus until I got a job researching NLP
• The book “On Intelligence”
• The Mind, body, soul discussion/book
• This lead me down the path thinking about how we truly learn something

• http://opencores.org/projects

• Interesting note: It's an ontology http://schema.org/
• also some history, Lenat built Cyc, which is a very complicated rule engine.

• AlphGo how does it compare to my algorithm?

• Clint suggested Graph viz or the dot file format

• Development Tasks
• first task is to create a Temperature based test case. Where 2 opposing corners are hot/cold. The Ai is a 3×3 square set of pixels and each pixel is a temperature sensor. The Ai can also move in a cardinal direction.
• Second task is to start targeting each Ai challenge found on a google search.

• the brain is constantly on. Input, output, input, output. The desire system changes the output to cause the brain to keep moving forward, which also changes the environments input. The sleep state disables all input so that the brain can reach a stale/neutral state.

• Neural Graph – title for the patent.
• after talking with clint:

0 0 0        l1n1(1)
1 0 0        l1n2(1) -> l1n1(.66)+l1n2(1) -> l2n1(1)
0 1 0        l1n3(1) -> l1n1(.66)+l1n2(.33)+l1n3(1)  -> l2n2(1) -> l2n1(?)+l2n2(1) ->  l3n1(1)

• maybe related to Graph Neural Networks

• growing a Neural Network – patent that.
• perception of time, it's just a cascading effect. a feedback loop.

• after reading this link, I was able to understand the solution I needed to have for true AI: http://stats.stackexchange.com/questions/39037/how-does-neural-network-recognise-images

• I keep coming back to this. So with a neural network, if it is looking at several pictures and the pictures are varying degrees of similarity how does the neural network know what the percentage of similarity is to each of the pictures? Currently, I would believe that the process is that someone sitting there is inputting a value to each of the images and training the neural network. But what if we used a base image of 100% accuracy and then used an FFT to compare it to other knowns or unknowns then feed the resulting variable as the result the NN needs to obtain.
• http://arxiv.org/abs/1312.5851
• http://www2.compute.dtu.dk/~abll/blog/fft_based_cnn/

• merge networks that are used to get to the same output. for example. I'm driving a car. I've determined that this specific place(image) means that I should accelerate. If I have a bunch of places that cause me to accelerate, merge the data sets into one and train a single network to know the result.

• Show the list of decisions for each action, would allow me to tune the ai steering it to better choices.

• link

Following the last post, This pattern would then activate the pathway in the brain that would be the predicated outcome. This activated pathway also activates emotions and these emotions relate or is desire. Our brain compares this predicted emotional response to other options available and compares these predicted emotional responses to determine which one the person wants to happen. This desire is also weighted against the current emotional state of the person.

Store sensor → read emotion → compare to desire → perform action → store sensor → read emotion → compare to desire → perform action

if you are at the first sensor, you can think through the change to figure out which action to perform to get to the emotion state that is desired.

Following what is written below, a real neuron is a fixed memory, not changing once created, referencing the video I saw about a person that lost the use of their hand and was retrained to use it and the scientist photographed the before and after showing the new neurons that had formed with the new ability. So looking at a ANN and using it to represent a single neuron, we can create a stored pattern for a newly formed neuron.

An actual neuron has multiple inputs and multiple outputs. The combination of the input along with the chemical balances in the neuron dictate how the outputs will look.

An artificial neural network node, has multiple inputs but only one output. So it may be better to use a neural network to represent a single neuron that exists in the human brain.

Desire is an input without and output. For example: a baby gets the input of hunger from the stomach, which the pattern in the brain triggers the sensor input of the mouth/tongue feeling the mom's nipple to suckle. But this is a memory recall and until the baby gets the actual input stimulus the activated nerves are the ones that stimulate the upset emotion, which grows more intense the longer it's activated. Once the nerves that are attached to the mouth/tongue are stimulated with the nipple and the taste of milk, this feeds back into the brain and then the nerves of the suckle action is activated. This input/output is stuck in a loop waiting for the stomach to activate the nerves of the “full” sensation. Then the nerves of the suckle action are stopped. This sequence is most likely hard wired in the lower brain.

So, how does memory form? an example to add to the baby wanting a nipple. When the mom tries to give the baby a bottle instead of the breast. The baby doesn't receive the same sensation from the bottle that is received from the breast. So the baby is not receiving the expected sensory input. But the baby gets a taste of the milk, which for the brain pattern is the stronger part of the input sensation. So the baby accepts this new input sensation because part of it is the right sensation. The brain starts to form new neurons that connect this new nerve input of the bottle feeling to the existing brain pattern of the suckling of the nipple. The more the baby receives this new input sensation, the stronger the pattern and the more the baby will want the bottle over the breast.

So the brain works by connecting the sensory nodes to each other through the neurons. for example: one rod in the eye has a lead into the brain. Then one cilia in the ear has one lead into the brain, etc for all sensor nodes. Those leads are then connected to one another by a neuron when they are stimulated. This neuron allows new neurons to be connected to it. This interconnected pattern forms a memory. To recall this memory is the excitation of those connected neurons back down to the sensor input. This re-action of the sensors allows the recall of the memory. This new sensor input is then applied to another thought pattern which allows for correlation. So, what creates the actual memory? repetition. The first time, is the first layer. etc, until 2 years have past. A child doesn't have any kind of cognition until they are about 2-3 years old. So layer upon layer is built and where there is similarities in sensory inputs over time, is where more neurons are created. Those areas of higher interconnected neurons are where our more stronger memories reside. These stronger memories are faces, words, places, etc.

Implement a system that can identify a pattern and then move the pattern to center in the array.

For example:

Move the eight to the center. The system can only move 1 up, 1 down, 1 left, and 1 right.

Bayesian Network API for potential use.

Ai Algorithms is a bunch of different algorithms.

More Algorithms is a list of algorithms.

OCC/OCEAN - emotion engine from a video conference called CIG2010

It's a note on the human infant growth process of the human mind.

infant four phase processing

growth phases of the human mind

http://www.solhaam.org/articles/humind.html

TV Show on the brain.