HLC 2020 12 01 Prediction of novelty


I am sorry that the sound quality was poor. That was not obvious during the meeting and I don’t know if any of us listen to the video before it is posted.

As I stated, introspection is just one tool for gaining insights and constraints. I have found it useful in all of our work. I don’t usually call it out but it is there. Other scientists use introspection too, even people who reject it! For example, when vision scientists talk about the stability of visual perception, that we are not aware of our saccades, that is based on introspection. The fact that our perception is stable during saccades tells us that there are some neurons whose firing is stable and other neurons whose firing is changing. The activity of neurons getting input from the retina must change with each new fixation. But there must be neurons whose activity is not changing, these represent your stable perception.

We can take this a step further. If cortical columns implement a common function, then we can deduce that the “changing pattern in some cells” being converted to the “stable pattern in other cells” must occur in each cortical column. This is the fundamental idea behind “pooling” or in our parlance “temporal pooling”. There are many examples like this. Again, introspection usually can’t tell you everything, but it can tell you a lot.


Hi Jeff. I guess I should have realised you would be watching…maybe I should have been more tactful.

Just to make my position clear: I think HTM and the theories immediately surrounding it are a brilliant step forward on a long journey. The idea of an SDR totally changed the way I think about brain(s), memory and sequencing. They feel right (whatever that means).

I distrust the links to neuroanatomy (dendrites and synapses, columns, 6 vs 4 layers) because of the lack of solid science. There are echos that seem plausible, but getting the science right is tough.

If we think about the kind of things going on in brains, there might be (say) 10 or 20 or 50 layers of functional refinement. HTM may give us hints about the 2 or 3 of those layers, introspection gives us a peek at the top 1 or 2. Almost all of our cognitive functioning happens at levels below introspection, and is already complete by the time we become aware of it. I regard introspection as seductive, occasionally useful but highly fallible and often totally wrong. It remains to be seen who is closer to the truth.

I saw a quote from a neuroscientist: ‘Show me, in a maggot’. When we can reliably describe and reproduce the computational behaviour of very simple brains, I will truly believe we are on track. Introspection won’t help with that either.