Eric Nehrlich, Unrepentant Generalist » Blog Archive » On Intelligence, by Jeff Hawkins

On Intelligence, by Jeff Hawkins

Posted: November 11, 2005 at 12:20 am in cognition, nonfiction

Amazon link

I’ve been meaning to read this for a while, and I added it to my last Amazon order, but didn’t get around to reading it until a few weeks ago. Jeff Hawkins was one of the driving forces behind Palm and Handspring, and now that he’s set for life, he’s indulging his childhood dreams of trying to understand the brain by starting the Redwood Neuroscience Institute, which is apparently now the Redwood Center for Theoretical Neuroscience. In this book, he pulls together a layman’s overview of neuroscience literature that he finds interesting, and then espouses his own theory of how the brain (or at least the neocortex) works.

Here’s the basic idea of his theory. The neocortex is composed of pattern-recognition elements that are wired to remember events that occur together. It’s a hierarchy of pattern-recognition elements that breaks people’s perception of their environment into manageable chunks. In other words, when I look around the room, I don’t see ten million pixels; I see my desk, the computer, the wall, etc. Even if I look at my desk at different angles, my brain perceives it as a single object.

Another aspect of this is that these elements are learning new patterns all the time. When we learn to drive and first get out into traffic, it’s terrifying because our brains are overloaded trying to filter all of the myriad visual information around us. As we grow more used to the speed of traffic and learn what’s relevant, the visual load is automated and pushed down to a subconscious level of the hierarchy. The same holds true for recognizing positions on a gameboard. None of this is particularly novel (I espoused a similar idea in my cognitive subroutines proposal).

The novel bit is that Hawkins noticed that our brains do more than perceive – they are actually continually making predictions. Here’s an obvious example: when you’re scanning your home, you can notice when something is NOT there. How is that possible? It’s not there, so you can’t see it. But your brain has developed a model of what IS there, and is making a prediction for what it should see, and when something doesn’t match its prediction, it alerts the conscious mind that something is wrong. This makes a ton of sense. Our brain adapts to the familiar, but if something changes, it needs to turn all of its attention to understanding why there’s a discrepancy. I thought this insight alone made the whole book.

As an aside, this also explains why most people suck at estimating probabilities. Our brains are wired to remember the abnormal and outlandish because they break the routine patterns that we have learned. We don’t remember the 99% of the time when things go as we expect them to, because it’s all handled subconsciously. So we significantly overestimate outlandish risks because they break the pattern and come to our conscious attention.

Another discussion that I liked was Hawkins’s description of “invariant representations” (which I allude to in my post on localized generalities). Basically, because the neocortex is hierarchical and each level is always making predictions, each level can notify the level below it what it should be looking for. In other words, if one level keeps track of things in my office, it can notify the level below it that it should be looking for a desk, and that it should figure out how to interpret the raw sensory input in such a way that it looks like a desk.

As another aside, this also explains why we often see what we expect to see. Our entire sensory system is designed around the principle that it should adapt its interpretation of raw sensory data to match what the levels above it think it should be seeing. This applies not only to physical things like desks, but also when we see patterns in random data, or “interpret” data in such a way as to support our point of view. Our brains are wired that way.

I thought the book was decent. The predictive aspect of the brain and the discussion of localized generalities were “Oh, wow” moments, as I immediately saw how they filled in gaps in some of my theories. Most of the rest of the book was an explanation where he handwaves how the current understanding of the neocortex can support his theory. There’s some minorly interesting stuff in there about how the various neocortical layers are connected in a way that might be hierarchical in the way he suggests, but that’s mostly of relevance to the neuroscience geeks.

I’m mostly kicking myself after reading it, though. I was moving along the same lines with my cognitive subroutines theory, but I was a couple years too late (as well as lacking any sort of intellectual rigor). And I’ve already discussed how my localized generalities post was the same idea as the “invariant representations”, without the neuroscientific backing. So I’ve got some good ideas; I just need to develop them, and do the legwork to support them more fully. In my copious free time.

P.S. Speaking of which, wow, that was quite a lull in posting for me. It’s been crazy. My company is trying to finish up projects for two different clients before Thanksgiving, so I’m spending a lot of energy there. I had the conference in LA a few weekends ago. Last weekend was a company outing to Monterey. There’s all sorts of other social stuff going on. So on the few nights that I’ve had at home alone, I’ve been so exhausted that I have just collapsed comatose onto the couch to watch TV rather than blogging. But I wanted to get up the CellKey prototype pictures tonight, and then figured I should clear out the backlog of book reviews that has built up. I actually finished all of these books a few weeks ago (and then spent last week catching up on my backlog of The Economist), but they’ve just been sitting on my desk since then.

16 Responses to “On Intelligence, by Jeff Hawkins”

  1. Juliana Coughlin Says:

    Welcome back, Eric. I enjoy reading your blog and was concerned when you went so long without posting.

  2. Eric Nehrlich, Unrepentant Generalist || Mike Murray on Hacking the Mind || July || 2006 Says:

    […] Another technique was injecting your own code to be run in somebody else’s brain. That means understanding the unconscious brain, which he says is all about patterns (shades of On Intelligence) and stories (I love stories). I loved the description of Milton Erickson (who I have to read now): “You walked into his office and sat down. Then, Milton told you a story and you found yourself changing.” That sounds so cool. […]

  3. Eric Nehrlich, Unrepentant Generalist || Persistent Patterns || August || 2006 Says:

    […] I actually want to revisit my completely uninformed picture of what goes on in our brain. Long-time readers may remember my series of cognitive subroutines posts, which were mostly superceded by the book On Intelligence. Basically, it’s the idea that our brain is just a pattern-forming and pattern-recognition machine. […]

  4. Eric Nehrlich, Unrepentant Generalist || Learn and latch || December || 2006 Says:

    […] On Intelligence, by Jeff Hawkins, posits a similar theory for how the brain learns. It’s a pattern recognition machine that doesn’t record new patterns until they have been used several times, indicating that they are successful patterns. […]

  5. Eric Nehrlich, Unrepentant Generalist || Patterns, stories and communities || December || 2006 Says:

    […] My thesis of the day is that the general patterns I was talking about are stories. I circle back to the topic of stories pretty regularly, as I find that stories are extremely powerful patterns that our brains are structured to absorb. For instance, I regularly tell stories that I don’t know the origin of; I don’t remember where I read or heard the story or even many of the specific details, but the general pattern of the story itself was memorable and sticks with me. I think the reason for that is that our brains are wired to remember patterns, not details, and our predilection for stories reflects that. […]

  6. Eric Nehrlich, Unrepentant Generalist || Made to Stick, by Chip and Dan Heath || February || 2007 Says:

    […] They looked at different advertising campaigns, from the Jared diet at Subway to “Don’t Mess with Texas”, and tried to extract the common themes and elements that they saw. Their acronym for what makes an idea sticky is SUCCESs: Simple, Unexpected, Concrete, Credible, Emotional and Story. You have to have a core idea that can be expressed in a single sentence or phrase. If you can’t boil it down to something that simple, it will never stick. It has to be unexpected and surprising – our brains are “wired to remember the abnormal and outlandish because they break the routine patterns that we have learned”. It must be concrete, because humans each interpret abstractions differently – only by making an idea specific and concrete can you assure that it will be remembered and passed on unchanged. It must be credible – if it is not easily verifiable, it will be dismissed as outlandish. Emotions play a strong role in memory, so it’s not surprising that ideas that evoke emotions are more sticky. And my favorite topic, stories, make ideas sticky because we remember stories as exemplars of patterns that matter to us. […]

  7. Eric Nehrlich, Unrepentant Generalist || Filling in the blanks part 2 || December || 2005 Says:

    […] to use Jeff Hawkins’s terminology, a set of cortical cells are activated by a stimulus, and based on the cells’ responses to […]

  8. Eric Nehrlich, Unrepentant Generalist || Telling the story of our lives || May || 2007 Says:

    […] But raw data is incomplete. It doesn’t mean anything. It needs us to make sense of it, to find the patterns, so that we can use those patterns to make future decisions. Without stories to bind it together, […]

  9. Eric Nehrlich, Unrepentant Generalist || Learning by repetition and memorization || January || 2008 Says:

    […] as possible to our unconscious brains. We have to build cognitive subroutines and embed the pattern recognition into our brains so that the conscious brain doesn’t need to think – we just recognize the input pattern and […]

  10. Eric Nehrlich, Unrepentant Generalist || Strategic Intuition and Expertise || June || 2008 Says:

    […] the intelligent memory hypothesis of how the brain works, which I assume is what is described by Hawkins in On Intelligence. I see how that would apply to expert intuition, which builds in common responses at lower layers […]

  11. Eric Nehrlich, Unrepentant Generalist || Intelligent organizations || June || 2008 Says:

    […] was: Can we apply the principles described by Jeff Hawkins’s model of the brain in On Intelligence to organization […]

  12. Eric Nehrlich, Unrepentant Generalist || Story Metrics || October || 2008 Says:

    […] and behave, which can provide guidance in interacting with others. In another variation of this, our brains are wired to remember deviations from the norm, as that was what enabled us to survive in a dangerous environment, so one could imagine that […]

  13. Eric Nehrlich, Unrepentant Generalist || How We Decide, by Jonah Lehrer || April || 2010 Says:

    […] optimize decisions among many conflicting dimensions. It is also extremely fast – it works by training neural circuits to recognize previously seen situations and respond quickly without involvi…. When we are developing our 10,000 hours of expertise, we are building the necessary neural […]

  14. Eric Nehrlich, Unrepentant Generalist || Cognitive Theories of Corporations || January || 2010 Says:

    […] view of how we think has been shown to be incomplete, at best. Books like The User Illusion and On Intelligence describe an unconscious mind which is doing so much processing and filtering that it can often […]

  15. Eric Nehrlich, Unrepentant Generalist » Blog Archive » How is your memory indexed? Says:

    […] Based on the On Intelligence theory of pattern-recognition, I wonder if my memory indexing on text/names is because most of my […]

  16. Eric Nehrlich, Unrepentant Generalist » Blog Archive » Thinking Fast and Slow, by Daniel Kahneman Says:

    […] intuition just because you are confident – you can only do so in regular situations where the subconscious pattern building machine can be […]

Leave a Reply

RSS feed

LinkedIn profile


My 1st #LT100 MTB… Thanks to @fatcyclist & @rebeccarusch for their clinics and to @TeamWBR for their support!

Recent Posts

  • The Leadville experience
  • My first Death Ride
  • Asynchronous Ask Me Anything
  • Raising money for World Bicycle Relief
  • I love my bike
  • Random Posts

  • Thoughts on manipulation
  • George Lakoff and politics
  • Networking
  • Randy Pausch lecture and feedback
  • Trading Randy Moss

  • Archives

  • Categories