More on this book
Community
Kindle Notes & Highlights
RNI was in all other ways doing well, so we decided to move it to UC Berkeley. Yes, the same place that told me I couldn’t study brain theory decided, nineteen years later, that a brain-theory center was exactly what they needed. RNI continues today as the Redwood Center for Theoretical
Remember this.
Numenta is an independent research company. Our primary goal is to develop a theory of how the neocortex works. Our secondary goal is to apply what we learn about brains to machine learning and machine intelligence. Numenta is similar to a typical research lab at a university, but with more flexibility.
The SFI of neuroscience?
Finally, there is the argument of extreme flexibility. Humans can do many things for which there was no evolutionary pressure. For example, our brains did not evolve to program computers or make ice cream—both are recent inventions. The fact that we can do these things tells us that the brain relies on a general-purpose method of learning. To me, this last argument is the most compelling. Being able to learn practically anything requires the brain to work on a universal principle.
This is the argument's essence.
The brain learns its model of the world by observing how its inputs change over time.
How does the neocortex, which is composed of thousands of nearly identical cortical columns, learn a predictive model of the world through movement?
The next itertion of the concept.
Tenet Number One: Thoughts, Ideas, and Perceptions Are the Activity of Neurons
Tenet Number Two: Everything We Know Is Stored in the Connections Between Neurons
Discovery Number Three: The Secret of the Cortical Column Is Reference Frames
The brain needs to know two things: what object it is touching (in this case the coffee cup) and where my finger will
be on the cup after my finger moves.
First, a reference frame allows the brain to learn the structure of something.
Second, by defining an object using a reference frame, the brain can manipulate the entire object at once.
Third, a reference frame is needed to plan and create movements.
entorhinal cortex, adjacent to the hippocampus.
All Knowledge Is Stored in Reference Frames
thinking is a form of moving. Thinking occurs when we activate successive locations in reference
This hypothesis can be broken down into the following components. 1. Reference Frames Are Present Everywhere in the Neocortex
2. Reference Frames Are Used to Model Everything We Know, Not Just Physical Objects
A column is just a mechanism built of neurons that blindly tries to discover and model the structure of whatever is causing its inputs to change.
3. All Knowledge Is Stored
Locations Relative to Reference Frames
4. Thinking Is a Form of Movement
We have proposed a simple explanation for why some columns are what columns and some are where columns. Cortical grid cells in what columns attach reference frames to objects. Cortical grid cells in where columns attach reference frames to your body.
How can cortical columns create models of things that we can’t sense? The trick is that reference frames don’t have to be anchored to something physical. A
The second trick is that reference frames for concepts do not have to have the same number or type of dimensions as reference frames for physical objects such as coffee cups.
The Existing View of the Neocortex
Scientists refer to this as a hierarchy of feature detectors.
feature detectors has been the dominant theory for fifty years.
It is not clear how the hierarchy of features theory even applies to touch or hearing.
problem or the sensor-fusion problem. More generally, the binding problem asks how inputs from different senses, which are scattered all over the neocortex with all sorts of distortions, are combined into the singular non-distorted perception we all experience.
