#because I imagine their tails function the same way as their animal counterparts do

[luna-the-cretar]

I will never not love Sarnax taking phrases too literally. Especially since it usually involves him trying to be helpful, and not understanding that it’s just a phrase

Like Victoria mentioning the phrase “catch more flies with honey than vinegar”, and this man was SO ready to give Victoria tips on how to actually catch flies. I just. I can’t. I love him so much.

It’s like Shepherd keeps saying, Sarnax is a little rough around the edges but he means well.

[commanders-sole-braincell]

some super speedy sketches cuz I can only think creatively if I’m drawing the thing (excuse the anatomy)

anyway - sylvair and mutations! (cuz sniffing at chimera’s and somantic mutations wasn’t enough for my grubby mitts!)

Also, hey big warning; if eyes, body horror, dead bodies (animal and human), and stuff like that isn’t your kinda thing - DO. NOT. GOOGLE. THE. TERMS. USED. HERE.

(if anyone’s desperate to read the wiki or look at images while dodging the more distressing ones hmu and I’ll help!)

I’m gonna shove my ramblings under the cut cuz A) I’mma write an essay for each and B) due to the nature of these mutations I am gonna touch upon body horror, and death and these are real mutations that do affect people!

Alright, strategically put the ones that are the least likely to throw people off at the top so I’m gonna ramble in order (top to bottom, left to right!) I’m also gonna be trying to summarize, generalize and describe these without writing a whole page so my info might not be 100% spot on!

Warnings for Animal death, body horror, death mention, infant death mention, eye horror mention, and bodily fluids and mess.

Harlequin Ichthyosis - this is a genetic disorder where the skin on the outside of the body hardens and cracks, leaving a jagged pattern across the skin of hardened plates which go a pale cream colour (and if I rcall correctly, possibly calcify?) ; this usually results in death within the first few months to weeks of life, after which the plates fall off, leaving tight, pink skin behind (essentially, the person almost has the appearance of being turned inside out). Recent developments in medicine mean that cases of people surviving this and living the rest of their lives with Ichthyosis are more common (granted alot of intensive care is needed). Breathing cna be restricted due to the tight skin (especially with the plates) and unfortunately ear or noses sometimes do not form on the infant.

For sylvari, I imagine this is probably pretty dangerous, as they can’t synthesize and, like the human counterparts, are very sensitive to the sun and other skin damages; I imagine the skin is like the inside of a plant, paler in colour to the sylvari’s actual skin - possibly with different texutres depending on type, where as the plates form as hardened bark or hard, dead leaves on the sylvari. They have to rely on other cultures for nutrients and clothing, and possibly may not glow at all.

Sirenomelia - (also known as the one I couldn’t draw to save my life!) This is where the individual is born with their legs fused, like a mermaid tail; hence the name. Degree of fusion ranges and can go up into the spine, and the person is unable to walk. While most notable individuals have passed, partly due to the fact this mutation can cause internal organs to not form (if I’m remembering correctly!), individuals do survive into adulthood and some have surgeries to improve quality of life!

For sylvari, I like to imagine this effects water-based plantlife sylvari more, with it varying from fused legs, to a fusion of the legs morphing in a way that it can act as a tail! Wheelcharis are used for land based adventures, and dresses and skirts may be more favoured! 

Also, if I’m remembering correctly, sylvari possibly have their brains in their lower back - which could mean that this could be the most potentially fatal mutation for sylvari, making surviving individuals rare - but also they’re sylvari and rules do not apply!

Polymelia - Simply put, polymelia is where an individual is bron with extra limbs - most are left over from a merge or conjoining twins - but there are cases with several extra limbs. Often these limbs are underdeveloped or deformed. usually this is not fatal, and these extra limbs can be safety removed if necessary.

Because this is sylvari, I thought that there’s bound to be those born who have working limbs, and those who came without (the kiddos in the pic share a nice mix between them) - and I like to think sylvari grow the same as humans (infant - child - teen - adult) in their pods, so limbs could be fully formed, or from one of the other stages! 

Cyclopia (the pink sylvari) - Cyclopia is a mutation where the eyes do not split and form a large eye in the centre of the forehead, and is often accompanied by no nose being formed, and organs may or may not form correctly; making the mutation fatal within a few hours or birth - the longest surviving creature with this was a goat, which reportedly survived up to a week after birth.

For sylvari, where organs don’t matter and the nose is a myth, cyclopia is probably survivable - assuming there’s a lid able to close around the eye and keep it moist. Emoting would probably be the biggest challenge, and bullying from other races may cause the most issues.

Now to tackle the three remaining vari!

These three are all various forms of Polycephaly mutations, sometimes known as two-headed. From left to right;

Wine and gold sylvari - this is a form of polycephaly known as Craniopagus (full name is often craniopagus parasiticus) Where the merging of twin embryos has occurred at the head, and the living twin has the underdeveloped twin’s head and even possibly torso attached to their head. There are even reports of individuals where they have a secondary face on the back of their head, that can function enough to smile. These cannot exist independently of each other, unlike conjoined twins. 

For sylvari, they could function with a twin attached to their skull (assuming it’s just their head, and not other parts - that could cause stress on the body) assuming the brain is not in the skull - or even if it is; theoretically the sylvari twins could function together!

Green twins - These represent a more common, I’d suppose, form of Polycephaly, known as Dicephalic Parapagus and function visually somewhat similar to conjoined twins. Survival depends entirely upon what factors the body has - seemingly those with more than two arms have a higher chance to survive to adulthood, but this is not necessarily a hard truth, as having two hearts and an individual spin attached to each head seems to be the most important factors for survival; as such, survival numbers are low. Interestingly, once helped through certain challenges, most twins can thrive on their own, although we are still learning more. Seemingly, most twins get control of one arm and one leg, although this may vary.

For sylvari, I imagine this isn’t much of a problem unless something happens to one of the twin’s heads - in which case the other twin could be at risk unless the other is removed (gotta get that angst in somewhere!) Granted sibling fights and getting along are probably a big deal for these sylvari, and they may need more nutrient to power their body. Also the fact they control separate sides of the body may actually aid them better in Tyrian life

Blue and gold sylvari - this is another form of polycephaly that is well known - Diprosopus - which is where the facial features are duplicated on the head of one body. While considered to be conjoined twinning, this is actually accused by a abnormal activity in the protein Sonic Hedgehog (stop laughing it’s a real thing). This often occurs with other congenital diseases, and individuals often don’t live very long, as other illnesses or issues are usually the cause of fatality. But there are instances of animals surviving with this, including a cat who lived to be 15 years old.

For sylvari, I imagine the issues that surround humans with this mutation, aren’t as fatal? They may have poorer health, or they may not! And while I’ve displayed one with a more textbook version of Diprosopus, this isn’t the only option, and a variety of features can pop up!

(fun fact! Low Sonic Hedgehog protein causes Cyclopia, too much Sonic protein causes Diprosopus! Sonic controls the width of facial features!)

Hoo boy I think i got them all I gotta go lie down, I read about Sonic protein and got dizzy bye ya’ll

[digimonreviews]

Perfect Digimon Wednesdays: MetalGreymon

Get your cybernetic ass back here.

So, I had a MetalGreymon review yesterday that I accidentally deleted, because I was on the phone instead of my proper internet, and also my hands are dumb and stupid. So it was down, the reblogs didn’t keep it, and so here it is again.

SO. PERFECT LEVEL DIGIMON. Originally, the Perfect level was the final form a Digimon could evolve to, hence the name’s very distinct-sounding finality. I mean, what could be better than Perfect? In any case, Ultimates came later, with the rise of the card game and the second set of virtual pets, the Pendulum series, which also overlapped with the release of the first anime, Digimon Adventure. By now, there are more Ultimate level Digimon than there are Perfect, so the name is now long since kind of a misnomer.

Interestingly enough, the Perfect level is what the dub calls “Ultimate”, while they call the dub version of the “Ultimate” level “Mega” instead. This can make talking about them rather confusing. But enough background info, let’s get into MetalGreymon properly.

MetalGreymon - Cyborg Digimon |  Attribute: Vaccine

Attacks: Giga Destroyer, Trident Arm, Metal Slash, Metal Slash Revision [Metal Slash Kai], Tera Destroyer, Over Flame, Metal Arm ; (Dub) Giga Blaster, Mega Claw, Metal Slash, Metal Slash II, Terra Destroyer, Powerful Flame

A Cyborg Digimon which has mechanized more than half of its body. The Metal Greymon of File Island were able to drastically extend their vital functions through remodeling, but their flesh portions could not hold out and were discolored blue. However, perfect Metal Greymon are Cyborg Digimon that succeed in evolving from Greymon, and draw out a stronger power. In order to evolve to Metal Greymon, it must fight its way through and defeat the formidable opponents who come against it. Also, Metal Greymon's offensive power is said to equal that of a single nuclear warhead, and if the likes of a low-level Digimon suffered that blow, it would be annihilated without leaving a trace. Its Special Moves are its "Trident Arm" made from enhanced Chrome Digizoid, and firing its "Giga Destroyer" organic missiles from the hatch on part of its chest.

- Translation by Wikimon.

Odds are if you’re a Digimon fan, this is the version of MetalGreymon you’re most familiar with. However, the MetalGreymon that was first introduced to the franchise in the very first virtual pet was actually very different, possessing the blue color-scheme that didn’t make it into the anime until much later in the form of Agumon’s “dark evolution” in season 2. The orange MetalGreymon didn’t appear until episode 20 of Digimon Adventure, and not until the fifth version of the Pendulum series. The Bandai lore, which is alluded to in the profile up there, is that the earlier, blue-colored MetalGreymon were inferior and couldn’t hold out after mechanization, while the orange ones successfully adapted to it. I imagine the out of universe explanation is that they wanted to have a version of MetalGreymon that looked more heroic (aka not a decaying blue cyborg flesh zombie), and kept visual continuity with Agumon’s other forms. This makes it another example of the “what could have been”-ness of everything involving Agumon and Greymon’s evolution lines in the anime.

MetalGreymon doesn’t discard all the visual elements of his viral counterpart, though. A lot of those earlier Cyborg Digimon had this very partsy, thrown together look, which you can see in MetalGreymon’s torn, ripped up wings, the torn flesh exposing cybernetics on his tail, and the way his new arm, chest and helmet look like they’ve been fused or bolted onto his body. Also, he’s grown hair for some reason, which will lead to a very hilarious line in the second season’s dub when Ken creates Kimeramon.

No, it’s real, I swear to god. Watch it, if only just to hear Derek Steven Prince scream dramatically: “...AND METAL GREYMON’S HAIR!”

But yeah, a lot of those earlier Cyborg and Machine Digimon had very ramshackle and thrown together looks, while later ones would appear more “put-together” as it were. I don’t necessarily mind that, as it’s another example of Agumon’s line introducing elements that will come later, and it also creates a sense of the technology used on these creatures being improved after the more experimental “concept” phase that guys like MetalGreymon here represent.

MetalGreymon can’t discard all of his virus counterpart’s creepiness either. While later games and other material would give him a fire-based attack, the only things we ever see him using in the anime are his extendable “Trident Arm” claw and the horrifying organic missiles he shoots out of his chest.

Seriously, they have mouths. WHY DO THEY HAVE MOUTHS?!

Anyway, MetalGreymon is a Digimon that embodies an interesting place in Digimon history. He’s very much a transitional phase between the very first era of the virtual pets to the next, possessing the same basic design but being adapted for the anime to fit in with an overall shift in marketing. But more than that, he’s just a very sharp, classic design, and he’ll have an influence on a lot of other characters to follow, just like the rest of Agumon’s evolutions do.

Some more directly than others.

In any case, MetalGreymon is actually my favorite of Agumon’s classic evolution line. You can’t go wrong with a Frankenstein’s Monster dinosaur, in the end. MetalGreymon gets...

FIVE STARMONS!

Join us next week when I hopefully actually post this on Wednesday and don’t freaking delete it again.

[skarmorydraws]

Team FAWN: Anais Armenus and Whitney Fitzgerald

After a bit of an absence, here are the other two members of Team FAWN! Aside from the theme of folk heroes, the four team members are all based on OCs of mine from various writing projects both planned and public. The boys are both derived from my original fiction, but the girls are both based on some of my agents written for the Protectors of the Plot Continuum; I figured that these two in particular were the best candidates for a RWBY AU facelift of sorts. Details under the cut!

Anais is, lore-wise, based on the Armenian folk heroine,  Anahit, whom you can read more about here, but she actually owes much more to Lapis Lazuli, who was not only one of my favorite agents to develop, but also had one of the longest stints in my creative history, and has been floating around the Interwebs since 2008. She started out as a Pokémon anime OC on DeviantArt, specifically for a writing project involving another artist's fakemon which has long since been abandoned, but since then she’s cropped up in various forms and incarnations in a couple of my writing projects before finally finding a home in the PPC. Anais, being her RWBY-verse counterpart, has inherited much of her high-strung, snappy personality, but I decided to give her a more sensual feel than Lapis, since I needed a way to make her character and fighting style distinct and Lapis’ outfit made me think of an exotic dancer. I also couldn’t not include the shark’s teeth that Lapis has in the PPC canon, so that led to Anais being a great white shark Faunus, which gave me a few good design cues for her outfit - it’s themed around dangerous fish, including sharks, and I imagine it’d be various shades of blue like the ocean with some tropical reef color flourishes. Her Semblance is teleportation, which is also a nod to a period when Lapis had a similar ability, though it has since been written out of the latter. Naturally, Anais is also aged up a great deal compared to Lapis, in fact being older than Fallow despite looking tinier - in fact, all four members of Team FAWN are the same age with the exception of Fallow, who got enrolled in Beacon a year early like how I went to college at a younger age than usual. :P Anais' weapon, Abanarsti (from the Armenian words for “sea” and “spear”), is a Dust Axe/Trident Amalgamate, a dual-headed staff whose trident/axe heads, which are shaped like shark tails, have revolver chambers like Myrtenaster which can be loaded with Dust, usually Water Dust, for various offense/defense purposes; the staff can also be split into dual hand-axes for close-quarters melee.

Anais, like Naja, lived in Vacuo during her youth, but most her childhood was far less memorable. In fact, she pretty much went off the grid for a while after her parents died when she was 10, wandering from town to town until she found her way into one of the few training academies in the nation that accepted Faunuses. She struggled through lots of racism during her academic career regardless, though - partly because everyone knew who she was the moment she opened her mouth, even before she could get the chance to speak. This gave her a highly detached temperament until, by happenstance, she ended up being accepted at Beacon, where she was schooled on the values of empathy and self-worth by her partner and fellow Faunus, Fallow, and the other members of Team FAWN. It was bonding with her teammates that helped her through the fall of Beacon, because until she realized that they more than filled the void left by her late family, Beacon was her only attachment and the place she considered her home... Now, her home is with Fallow, with whom she’s formed a sibling-like relationship, as well as Whitney and Naja who regard her as one of their closest friends and as a reliable means of keeping her teammates’ more overzealous tendencies in check.

Whitney’s look is unashamedly lifted from the AU outfit for the female Wii Fit Trainer in this picture by CoronaDiTempesta, and all credit for the original concept goes to them, though I made a number of changes to avoid outright plagiarism such as including bandages on her arms and legs like a Muay Thai boxer (as seen on the male WFT in the source pic) and lots of scars all over her upper body. Her lore basis is Étaín, the Celtic heroine of the Tochmarc Étaíne, who was identified as a sun goddess by linguistics scholar T.F. O'Rahilly, but she’s also based on the aforementioned Wii Fit Trainer as well as another PPC agent of mine, simply known as Whitney. I came up with Agent Whitney and her partner purely as proxies to dip my toes into missions involving video-game-specific continua, but I’ve slowly taken a liking to them both to the point where expies of them may show up in my original writing as well eventually - RWBY!Whitney, in fact, is pretty much Agent Whitney with a different outfit, abilities more fitting of a Remnant native, and a Solar-Powered Telescoping Flail called Lorganfaid, after the Irish Dagda god’s magic staff. Said flail functions like a giant wrecking ball with a retractable chain, so it can be used as a close-range bludgeon or a mid-range whip with a big spiky death orb at the end, and paired with her Solar Absorption Semblance - i.e. absorbing sunlight to power herself up or regenerate Aura - it can generate a plasma field that can burn things while smashing them to bits.

Whitney and her brother, Wynn, were originally from Mistral’s capital, and were raised by a single mother (modeled after an older version of Dawn from Pokémon Diamond and Pearl, who was another one of my waifus back in the day :P), but since their mom was a sculptor and had to spend a lot of time doing commission work, they had to eke out a living on their own as street performers during the daytime - and vigilantes in the night. The two of them were inseparable as children, but went their separate ways when Wynn got accepted into Haven, while Whitney found her way into Beacon instead, which is where she met her other teammates and her partner, Naja, who may or may not have a crush on her. Whitney is the Only Sane Woman of the team, being calmer and more rational than all three of her teammates combined, as well as the first one to respond with justified incredulousness to whatever craziness the gang encounters, though she’s long since learned to stop questioning things in general out of tactfulness. She’s very collected even in the midst of battle, likes to incorporate calming yoga routines into her techniques of bashing Grimm to oblivion, and spends almost all of her spare time either meditating or cooking the healthiest food she can for the team. As such, it’s difficult to incite her into intense emotions, but woe betide anyone stupid enough to do so - only a few of the individuals who’ve genuinely angered her have managed to survive the ensuing carnage, and all of them have scars.

RWBY © RoosterTeeth

Team FAWN © me

[mike-ac]

Jeff’s views on AI, Neocortex

Thus, to understand how the brain works, you need to start with the neuron. Your neocortex has about 30 billion of them. A typical neuron has a single tail-like axon and several treelike extensions called dendrites. If you think of the neuron as a kind of signaling system, the axon is the transmitter and the dendrites are the receivers. Along the branches of the dendrites lie some 5,000 to 10,000 synapses, each of which connects to counterparts on thousands of other neurons. There are thus more than 100 trillion synaptic connections.

When a neuron fires, an electrochemical spike travels down the neuron’s axon and crosses synapses to other neurons. If a receiving neuron gets enough input, it might then fire in response and activate other neurons. Of the 30 billion neurons in the neocortex, 1 or 2 percent are firing at any given instant, which means that many millions of neurons will be active at any point in time. The set of active neurons changes as you move and interact with the world.

The neocortex stores these patterns primarily by forming new synapses. This storage enables you to recognize faces and places when you see them again, and also recall them from your memory. For example, when you think of your friend’s face, a pattern of neural firing occurs in the neocortex that is similar to the one that occurs when you are actually seeing your friend’s face.

Remarkably, the neocortex is both complex and simple at the same time. It is complex because it is divided into dozens of regions, each responsible for different cognitive functions. Within each region there are multiple layers of neurons, as well as dozens of neuron types, and the neurons are connected in intricate patterns.

The neocortex is also simple because the details in every region are nearly identical. Through evolution, a single algorithm developed that can be applied to all the things a neocortex does. The existence of such a universal algorithm is exciting because if we can figure out what that algorithm is, we can get at the heart of what it means to be intelligent, and incorporate that knowledge into future machines.

But isn’t that what AI is already doing? Isn’t most of AI built on “neural networks” similar to those in the brain? Not really. While it is true that today’s AI techniques reference neuroscience, they use an overly simplified neuron model, one that omits essential features of real neurons, and they are connected in ways that do not reflect the reality of our brain’s complex architecture. These differences are many, and they matter. They are why AI today may be good at labeling images or recognizing spoken words but is not able to reason, plan, and act in creative ways.

Our recent advances in understanding how the neocortex works give us insights into how future thinking machines will work. I am going to describe three aspects of biological intelligence that are essential, but largely missing from today’s AI. They are learning by rewiring, sparse representations, and embodiment, which refers to the use of movement to learn about the world.

Learning by rewiring: Brains exhibit some remarkable learning properties. First, we learn quickly. A few glances or a few touches with the fingers are often sufficient to learn something new. Second, learning is incremental. We can learn something new without retraining the entire brain or forgetting what we learned before. Third, brains learn continuously. As we move around the world, planning and acting, we never stop learning. Fast, incremental, and continuous learning are essential ingredients that enable intelligent systems to adapt to a changing world. The neuron is responsible for learning, and the complexities of real neurons are what make it a powerful learning machine.

In recent years, neuroscientists have learned some remarkable things about the dendrite. One is that each of its branches acts as a set of pattern detectors. It turns out that just 15 to 20 active synapses on a branch are sufficient to recognize a pattern of activity in a large population of neurons. Therefore, a single neuron can recognize hundreds of distinct patterns. Some of these recognized patterns cause the neuron to become active, but others change the internal state of the cell and act as a prediction of future activity.

Neuroscientists used to believe that learning occurred solely by modifying the effectiveness of existing synapses so that when an input arrived at a synapse it would either be more likely or less likely to make the cell fire. However, we now know that most learning results from growing new synapses between cells—by “rewiring” the brain. Up to 40 percent of the synapses on a neuron are replaced with new ones every day. New synapses result in new patterns of connections among neurons, and therefore new memories. Because the branches of a dendrite are mostly independent, when a neuron learns to recognize a new pattern on one of its dendrites, it doesn’t interfere with what the neuron has already learned on other dendrites.

This is why we can learn new things without interfering with old memories and why we don’t have to retrain the brain every time we learn something new. Today’s neural networks don’t have these properties.

Neuron Mimicry Explained

Intelligent machines don’t have to model all the complexity of biological neurons, but the capabilities enabled by dendrites and learning by rewiring are essential. These capabilities will need to be in future AI systems.

Sparse representations: Brains and computers represent information quite differently. In a computer’s memory, all combinations of 1s and 0s are potentially valid, so if you change one bit it will typically result in an entirely different meaning, in much the same way that changing the letter i to a in the word fire results in an unrelated word, fare. Such a representation is therefore brittle.

Brains, on the other hand, use what’s called sparse distributed representations, or SDRs. They’re called sparse because relatively few neurons are fully active at any given time. Which neurons are active changes moment to moment as you move and think, but the percentage is always small. If we think of each neuron as a bit, then to represent a piece of information the brain uses thousands of bits (many more than the 8 to 64 used in computers), but only a small percentage of the bits are 1 at any time; the rest are 0.

Let’s say you want to represent the concept of “cat” using an SDR. You might use 10,000 neurons of which 100 are active. Each of the active neurons represents some aspect of a cat, such as “pet,” or “furry,” or “clawed.” If a few neurons die, or a few extra neurons become active, the new SDR will still be a good representation of “cat” because most of the active neurons are still the same. SDRs are thus not brittle but inherently robust to errors and noise. When we build silicon versions of the brain, they will be intrinsically fault tolerant.

There are two properties of SDRs I want to mention. One, the overlap property, makes it easy to see how two things are similar or different in meaning. Imagine you have one SDR representing “cat” and another representing “bird.” Both the “cat” and “bird” SDR would have the same active neurons representing “pet” and “clawed,” but they wouldn’t share the neuron for “furry.” This example is simplified, but the overlap property is important because it makes it immediately clear to the brain how the two objects are similar or different. This property confers the power to generalize, a capability lacking in computers.

The second, the union property, allows the brain to represent multiple ideas simultaneously. Imagine I see an animal moving in the bushes, but I got only a glimpse, so I can’t be sure of what I saw. It might be a cat, a dog, or a monkey. Because SDRs are sparse, a population of neurons can activate all three SDRs at the same time and not get confused, because the SDRs will not interfere with one another. The ability of neurons to constantly form unions of SDRs makes them very good at handling uncertainty.

Such properties of SDRs are fundamental to understanding, thinking, and planning in the brain. We can’t build intelligent machines without embracing SDRs.

Embodiment: The neocortex receives input from the sensory organs. Every time we move our eyes, limbs, or body, the sensory inputs change. This constantly changing input is the primary mechanism the brain uses to learn about the world. Imagine I present you with an object you have never seen before. For the sake of discussion, let’s say it’s a stapler. How would you learn about the new object? You might walk around the stapler, looking at it from different angles. You might pick it up, run your fingers over it, and rotate it in your hands. You then might push and pull on it to see how it behaves. Through this interactive process, you learn the shape of the stapler, what it feels like, what it looks like, and how it behaves. You make a movement, see how the inputs change, make another movement, see how the inputs change again, and so on. Learning through movement is the brain’s primary means for learning. It will be a central component of all truly intelligent systems.

This is not to say that an intelligent machine needs a physical body, only that it can change what it senses by moving. For example, a virtual AI machine could “move” through the Web by following links and opening files. It could learn the structure of a virtual world through virtual movements, analogous to what we do when walking through a building.

This brings us to an important discovery we made at Numenta last year. In the neocortex, sensory input is processed in a hierarchy of regions. As sensory input passes from one level of the hierarchy to another, more complex features are extracted, until at some point an object can be recognized. Deep-learning networks also use hierarchies, but they often require 100 levels of processing to recognize an image, whereas the neocortex achieves the same result with just four levels. Deep-learning networks also require millions of training patterns, while the neocortex can learn new objects with just a few movements and sensations. The brain is doing something fundamentally different than a typical artificial neural network, but what?

Hermann von Helmholtz, the 19th-century German scientist, was one of the first people to suggest an answer. He observed that, although our eyes move three to four times a second, our visual perception is stable. He deduced that the brain must take account of how the eyes are moving; otherwise it would appear as if the world were wildly jumping about. Similarly, as you touch something, it would be confusing if the brain processed only the tactile input and didn’t know how your fingers were moving at the same time. This principle of combining movement with changing sensations is called sensorimotor integration. How and where sensorimotor integration occurs in the brain is mostly a mystery.

Our discovery is that sensorimotor integration occurs in every region of the neocortex. It is not a separate step but an integral part of all sensory processing. Sensorimotor integration is a key part of the “intelligence algorithm” of the neocortex. We at Numenta have a theory and a model of exactly how neurons do this, one that maps well onto the complex anatomy seen in every neocortical region.

What are the implications of this discovery for machine intelligence? Consider two types of files you might find on a computer. One is an image file produced by a camera, and the other is a computer-aided design file produced by a program such as Autodesk. An image file represents a two-dimensional array of visual features. A CAD file also represents a set of features, but each feature is assigned a location in three-dimensional space. A CAD file models complete objects, not how the object appears from one perspective. With a CAD file, you can predict what an object will look like from any direction and determine how an object will interact with other 3D objects. You can’t do these with an image file. Our discovery is that every region of the neocortex learns 3D models of objects much like a CAD program. Every time your body moves, the neocortex takes the current motor command, converts it into a location in the object’s reference frame, and then combines the location with the sensory input to learn 3D models of the world.

In hindsight, this observation makes sense. Intelligent systems need to learn multidimensional models of the world. Sensorimotor integration doesn’t occur in a few places in the brain; it is a core principle of brain function, part of the intelligence algorithm. Intelligent machines also must work this way.

These three fundamental attributes of the neocortex—learning by rewiring, sparse distributed representations, and sensorimotor integration—will be cornerstones of machine intelligence. Future thinking machines can ignore many aspects of biology, but not these three. Undoubtedly, there will be other discoveries about neurobiology that reveal other aspects of cognition that will need to be incorporated into such machines in the future, but we can get started with what we know today.

From the earliest days of AI, critics dismissed the idea of trying to emulate human brains, often with the refrain that “airplanes don’t flap their wings.” In reality, Wilbur and Orville Wright studied birds in detail. To create lift, they studied bird-wing shapes and tested them in a wind tunnel. For propulsion, they went with a nonavian solution: propeller and motor. To control flight, they observed that birds twist their wings to bank and use their tails to maintain altitude during the turn. So that’s what they did, too. Airplanes still use this method today, although we twist only the tail edge of the wings. In short, the Wright brothers studied birds and then chose which elements of bird flight were essential for human flight and which could be ignored. That’s what we’ll do to build thinking machines.

As I consider the future, I worry that we are not aiming high enough. While it is exciting for today’s computers to classify images and recognize spoken queries, we are not close to building truly intelligent machines. I believe it is vitally important that we do so. The future success and even survival of humanity may depend on it. For example, if we are ever to inhabit other planets, we will need machines to act on our behalf, travel through space, build structures, mine resources, and independently solve complex problems in environments where humans cannot survive. Here on Earth, we face challenges related to disease, climate, and energy. Intelligent machines can help. For example, it should be possible to design intelligent machines that sense and act at the molecular scale. These machines would think about protein folding and gene expression in the same way you and I think about computers and staplers. They could think and act a million times as fast as a human. Such machines could cure diseases and keep our world habitable.

In the 1940s, the pioneers of the computing age sensed that computing was going to be big and beneficial, and that it would likely transform human society. But they could not predict exactly how computers would change our lives. Similarly, we can be confident that truly intelligent machines will transform our world for the better, even if today we can’t predict exactly how. In 20 years, we will look back and see this as the time when advances in brain theory and machine learning started the era of true machine intelligence.

About the Author

Jeff Hawkins is the cofounder of Numenta, a Redwood City, Calif., company that aims to reverse engineer the neocortex.