Category Archives: Brain

Prediction equals intelligence

To end this series of blog posts, I’m going to talk about artificial intelligence and the need for engineers to broaden their knowledge on subjects outside their specific field of study.

The following TED Talk by Jeff Hawkins tells us exactly why we’ll never develop good artificial intelligence, if we’re to lazy to look at the underlying brain science.

Why A.I. needs brain science

csdcvsdvsdvsd
This TED talk seems to be centered around knowing our brains … and things

Up until now, a lot of the current research effort has been focused on reproducing human behavior. Alan Turing famously launched the Turing test in his paper “Computing Machinery and Intelligence” (1950) in an attempt to provide a metric of performance for artificial intelligence.

In terms of this test, a machine is to be considered intelligent if it is able to imitate human behavior. In other words, a human being shouldn’t be able to distinguish that he/she is talking with a machine instead of another human.

Jeff Hawkins however, debates that true intelligence is achieved by having a memory systems that continuously stores what we experiences and plays back similar experiences to help us predict what will happen next.

Those who have read my latest blog posts shouldn’t be surprised that a lot of what our brain is doing is predicting the future.  (Those who haven’t, I strongly recommend you read “Really, I’m just guessing! – Your brain” 😉 ).

Jeff Hawkins has a brilliant, yet simple way, to prove that we are really constantly trying to predict the future:

Because you’re intelligent and you speak English, you know what word is at the end of this …

sentence.

We don’t have to hear him say the last word. Out of experience we know what it will be, we hear it in our mind.

Why is this relevant?

The altered door experiment

[…] you have a door at home, and when you’re here, I’m changing it, I’ve got a guy back at your house right now, moving the door around, and they’re going to take your doorknob and move it over two inches. And when you go home tonight, you’re going to put your hand out there, and you’re going to reach for the doorknob and you’re going to notice it’s in the wrong spot, and you’ll go, whoa, something happened. It may take a second to figure out what it was, but something happened.Now I could change your doorknob in other ways. I can make it larger or smaller, I can change its brass to silver, I could make it a lever. I can change your door, put colors on; I can put windows in. I can change a thousand things about your door, and in the two seconds you take to open your door, you’re going to notice that something has changed.

Now, we all know the engineering approach: let’s make a huge database that contains every property of the door and then we’ll just check them one by one. But is that what’s really going on inside our brains? No!

What really happens is that we make a prediction every time we grab for that doorknob. We have an expectation of how the material will feel, what kind of shape it has, where we have to grasp, … If our prediction is of even slightly, we immediately know something has changed.

This is exactly why intelligence equals prediction and the domain of artificial intelligence needs some lessons in brain science.

Afterthoughts

This TED Talk was given in 2003, in the last decade Jeff Hawkins has made a lot of progress . For those of you who would like to learn more about this subject:

Video: Building Brains to Understand the World’s Data (Google Tech Talk by Jeff Hawkins)
His company specialized in machine intelligence: Numenta

Music pattern that makes your brain go wild!

Today’s pop songs are often criticized because of their bland, boring and unoriginal lyrics and melodies. But is that really the case? And more importantly: if it is, why do we put up with it?

Songs by the dozen

As I mentioned earlier, the human brain is a wonderful thing. It is capable of decoding all of the information around us at an astounding rate. A daunting task! Lets give our brains a break shall we? Lets give it some more enjoyable data to process:

Remember all those great pop songs? Frighteningly similar aren’t they?

The I V vi IV chord progression

Repeat: I V vi IV, I V vi IV, …

The amazing people at Hooktheory analyzed 1300 songs and found that we do favor certain “sounds” above others.  This popular “I V vi IV” chord progression can be found in thousands of songs because it feels natural to us. We don’t know why, we just like it a lot!

I know, (over-)analyzing music is wrong. But there are some lessons to be learned. Indeed, for once pop culture might actually learn us something! 😉 As chaotic as we might seem in our decision-making, there are a lot of patterns going on inside our heads. Understanding how the human brain, body or society work is ultimately down to finding and explaining these patterns.

PS Be sure to try their interactive database!

Alt text: You know what happens when you assert--you make an ass out of the emergency response team. Source: XKCD

“Really, I’m just guessing!” – Your brain

We like patterns! Our brain likes to find them even when there aren’t any to be found. This podcast by Scientific American explains, very briefly, two studies that asked participants too look for trends in artificial stock market data and images in video static. In both cases the subjects found patterns were there weren’t any, this is called illusory pattern perception.

Source: Scientific American

The reason for this pattern seeking behavior is simple. Our brain needs to process a lot of data, which is oftentimes incomplete. Detecting patterns can also be helpful from a survival perspective. Being able to pick out changes in your surroundings is key to being able to act quickly in a dangerous situation.

It gets worse! You’re brain is not only scanning your senses to detect patterns, but it’s also making stuff up. The amount of raw data available to parse is enormous. Whereas the processor in your computer would (slowly) start processing it bit by bit, our brain performs a different trick. It assumes its smart enough to select only the most important information and fill in the blanks by logical deduction.  Good luck with that!

As any student that has tried to apply this same methodology to their studies can confirm: this isn’t a flawless system. But it does allow us to quickly react to our surroundings and make intelligent decisions based on incomplete data. A field in which robotics still have a long way to go. For instance, it’s because of this system that we can (mentally) track a pedestrian that momentarily is obscured by obstacles along the line-of-sight.

Based on past experiences our brain creates a complex model of the way everything around us interacts. But this modus operandi also makes our brain susceptible to deception. We often overestimate our ability to grasp what’s going on in our surrounding, a vulnerability that is exploited by magicians and pickpockets around the world.

What can you take away from this? Your brain is a powerful beast, learn to respect it and learn the limits of its powers. Nervous for a presentation and certain that everybody will notice it? It probably isn’t (entirely) true, your mind is just very good at convincing you.

Remember, sometimes we  do assume a bit too much.

Alt text: You know what happens when you assert–you make an ass out of the emergency response team. Source: XKCD