A few key questions which I came across while reading the book and my thoughts on it.

  1. Who are we? As a lot dependent on how our neurons are trained? The state of all our neurons and their collective parameters. So the entity which we refer to as "me" is nothing but a particular stage in the training of neural network. It is constantly changing. The decision which you take now in a given condition, may be very different from say 10 yrs ago - as your neural net has changed.

  2. Our past is not a faithful reconstruction. The way we remember the past can be very different from how it actually happened? So, who we are, which is dependent a lot on our memories - is not a reflection of reality but what we chose to remember from our past.

  3. Consciousness as an emergent property - Just an emergent property from the activity of millions of neurons. Like traffic is an emergent property from the movement of all the cars. When the cars move, there is nothing called "traffic", traffic emerges out of interaction of multitudes of vehicle. But why does this emergent property appear so real?

  4. If there is no memory, there is no sense of time - There has not been any independent verification of time!

  5. Decision making and free will - Apparently our lower brain makes decision even before we are consciously aware of it. So do we really decide or it is just a story which our neocortex tells us?

  6. Are we living in a simulation? An interesting argument by Nick Bostrom

  7. Our internal model is low resolution but up-gradable - similar to what John Deane of Google Brain project suggests in this lecture. The best approach is to build a huge model which can give results for thousands of problems rather than individual models trained for specific. Is this the reason why we are a general purpose machine, rather than very good at specific tasks. As Henlein used to say -

“A human being should be able to change a diaper, plan an invasion, butcher a hog, conn a ship, design a building, write a sonnet, balance accounts, build a wall, set a bone, comfort the dying, take orders, give orders, cooperate, act alone, solve equations, analyze a new problem, pitch manure, program a computer, cook a tasty meal, fight efficiently, die gallantly. Specialization is for insects.”

― Robert A. Heinlein