Sub Conscious Learning System

I had a thought, today. It was for a type of learning which seemed quite natural, but I had not even imagined being able to implement, previously. It is a system for self-scoring. As you might know, in general evolutionary algorithms, a computer program is given a score based on how well it functions, and it's children carry on that score, and build onto it. Eventually, after many generations, it gets smarter and smarter. However, with this system, if forces the entire species to lean as a whole, rather then individually. This works perfectly fine if the algorithm is designed to only master a single task, even if it's complex. But what about more complex tasks?

How could an artificial intelligence agent be designed, so that it can make it's own choices. Score it's own actions and abilities. This is an important trait for agents who want to have any hope in thriving in a complex environment, where more then a single action must be scored. This is a critical base for higher level thinking machines. Machines that learn strategy, and can plan out actions ahead of time. Taking into consideration events which only they specifically have encountered, not their previous generations.

Here is my proposal. For this system, the original generation based learning algorithm is still in place. This judges actions solely around things such as survival of the individual, and expanding the population. But there is also another learning system in play, here. The second learning system is per agent, and effects only their brain. This is constantly updating, as well.

In this system, imagine we have an entire AI brain network. Neurons and all. Now, take a chunk of it. Say, 25% or so, and mark this as the subconscious. This part is unable to be edited by the agent. In addition, this chunk is close to the end or the network, and all linked together closely. Yes, there are many connections going in, and also several going out. Though, in the middle of these, there are "emotion" neurons. These release emotional responses based on their input. Positive input, results in a positive output. Negative input, results in a negative output. Highly positive input, results in a highly positive output. And so on. Now, these emotional responses are the "score" values for the agent. It wants these to be as high as possible. So it is constantly weighing in different neuron values for the rest of the brain to try to influence the emotions. Now, the main evolutionary algorithm still wants the brain to function a certain way, to accomplish it's overall tasks. Survive, and thrive.

When a new agent is born, it's default brain state is given to it by the evolutionary algorithm. It also decides which parts of the brain are editable, or not. (This network is also assuming the same setup as the one I described in my article "Smoother Node Map Learning".)

By doing it this way, the agent is allowed to learn and adapt to it's environment at it's own pace, while the main algorithm gives a general path for everyone to follow. Both algorithms fight each other, and also work together to achieve a goal.

As each agent is it's own brain, and learning path, each one will have it's own personality, goals, and so on. Each will behave in their own way, but still follow the same overall instincts given to them when they are born.

I am quite excited to see how this plays out, so I will be playing with the code for it. (Though most likely I'll just get lazy and never finish it, as is the case for most of these ideas.)

Why can't machines feel emotion?

This is a heavy topic, in my opinion. This is something that has been thrown around as a artificial intelligence stereotype since the topic of artificial intelligence via computer was thought up.

Maybe I should start with why this bias against machines was first used. In early days of computers, it was assumed that no matter how much math a computer could do, a human would always be more intelligent. Eventually, a computer was designed specifically to play chess. After beating a professional chess player with little effort, computer scientists began to see that there really was potential in computer programs surpassing human level intelligence. The idea of AI has been thrown around for centuries. Even Leonardo Da Vinci once built a robot (armor, that was controlled by a series of ropes and pulleys), to simulate AI. But now, this seemed like it was actually within reach.

Years later, the first "chat bot" was a created. A program that was designed to respond to human sentences, in a was they was comprehensible. Many people even thought that there was just talking to a regular person over a computer. However, though the program formed correct speech, and was able, to an extent, respond correctly to human input, the responses all seemed emotionless and heartless. This is where the famous serotype that all machines were "forever emotionless."


I disagree with this, completely. Though, to explain my logic, I should explain what "emotion" is. Or at least what it is in my opinion. I believe that what we think of as emotion, is nothing more then a complex scoring system. Whether you believe in evolution or not is irrelevant for this point. Simple adaptation, a quick and observable event, is all the proof that is needed to convey this reasoning. People who are loving are more likely to have families, kids, and relationships, etc. Thus, they can pass down this mental trait to their children, grandchildren, and further down the line. So imagine if a person was unable to feel. They would have nothing to motivate them to live. To encourage them to have families, or take care of those families. Their chances of having children are significantly low. Even if they did, their children would share this trait and the pattern would continue until the trait finally woven out of their family tree, from the mental traits of the other parent.

So emotion is definitely important to keep a family tree going. It can also been observed that more emotional people can also strengthen this point, as they are even more encouraged to have families, and similar. So emotion is a key factor in creating families. Ok, simple enough.

Let's move on to another point. Emotions such as fear, happiness, anger. With fear, fear keeps people alive. People with little fear are more likely to do stupid stuff, and get themselves killed. Thus, fear keeps you alive longer, and gives you more time to start a family and carry on that trait of fear to your children. Anger, gives you a boost of adrenaline to fight off threats and protect yourself, or loved ones from what your brain sees as danger. (Mental or physical.) Happiness, pleasure, and similar, gives you an objective to work towards; a purpose in life. A feeling of pride when you hold your child, or a gleam across your face when you see someone else you care about smile. That motivation also keeps us alive as a society. The drive to build better tools, stronger shelter, faster means of travel. Each of these helping the survival of humans immensely. Sadness, tells us points or things to avoid. Pain causes sadness, and pain hurts the body. So stay away from what causes you pain. Better, and longer life. Etc. I could keep going for hours, but I feel I've made my point.

Emotion has given us the ability to learn as well. Imagine if a baby was born without the ability to feel emotion in any way. It wouldn't be able to learn even simple tasks, as it would be unable to answer the simple question, "why?"

"Why should I walk? Why should I read and write? Why should I do this instead of that?"

Without being able to understand why it needs to do something, it has no reason to do it. No push. No encouragement. No remorse, no regrets, nothing to aim for, or avoid. Pain would mean nothing. Pleasure would mean nothing. It would uncaring do dangerous things without caring if it was hurt in the process. Simple just because it could. There's also a good chance it wouldn't even move. As why bother wasting the energy?

Emotion is critical in learning. And in social situations, more emotion is much stronger for learning, and survival as a whole. So is it not sort of like a goal? People always seek out to please their emotions. Avoid pain, seek pleasure, try to be happy, protect yourself with anger or fear as necessary, etc. In simple adaptation, traits that are better for a being's survival are more likely to be traced to their kids, grand kids, and enviably everyone generations down the road. Almost like a score on how helpful that trait was.


AI is no different. It has a goal, and gets a score based on that goal. If it gets a low score, it's sad. A higher score makes it happy. It is constantly surviving towards whatever makes the program said makes it happy. (I.e. Gives it a higher score.) Using multiple score situations, the AI basically can feel multiple emotions. The current score being it's current emotion. Tracking scores over long term could even translate towards long term goals, hopes, or dreams. As each AI learns in their own way, they each have their own personalities, and ideas of what makes them happy, and what doesn't. Depending on how the scores are set up, AI can have the exact same emotions as a human can. Or more, or less. Or a set that's completely different from ours in every way.

So why can't an AI feel emotion? It very well, can.



So, did I screw up somewhere? Disagree with something, or simply want to add your own input? Go ahead and leave a comment. :)