Have you ever realized that the big ideas in Deep Learning are just formulations of very old ideas. Generative Adversarial Networks (GANs) @goodfellow_ian is just Hegel's dialectic (i.e. thesis and antithesis hence synthesis).
Thanks to Twitter, I've stumbled upon two must-watch videos that reveal a very important aspect of human minds that we often ignored. The brain's purpose is homeostasis, but what happens when we lose this purpose?
In the first video, Jill Bolte Taylor describes her experience when a stroke damaged the left hemisphere of her brain.
It is important to watch that video before proceeding. In the next video, the author describes his experience with a syndrome described as 'depersonalization'. aeon.co/videos/the-dar…
Nobody really has a good theory of how brains work. Yet we keep hearing people saying that artificial neural networks are not biologically plausible. Who anointed these folks to be the thought police of what is plausible?
A mistake that too many make about artificial neural networks is that they are implementation models (see: Marr's level of explanation). They are not! They are algorithmic models. When you realize this, the question of biological plausibility should be thrown out.
I think Pylyshyn's mapping of the semantic, syntactic and physical to Marr's computational, algorithmic and implementation is just wrong.
Do you think fractals (i.e. iterative and self-similarity) are weird? Well, it isn't as weird as biological iterative processes. medium.com/intuitionmachi…
What's even weirder is that humans have an intuition that something appears organic. What does it actually mean to have an organic design?
Christopher Alexander, an architect, who wrote 'A Pattern Language' that has immensely influenced software development, wrote four books exploring this idea (see: Nature of Order).
Does anyone ever become conscious of how they know how to ride a bicycle? Have you ever tried explaining to a child how to ride a bicycle? The child learns when they overcome their fear rather than understanding your explanation.
We understand how to ride a bike becoming familiar with the interaction. Although a bike is an unnatural thing with wheels, we are still able to mentally make it an extension of our bodies.
We are never really conscious of how we are able to do many things we do in life. If we did, then we could easily specify the rules for a robot to do the same thing. But we don't know how we do things.
I suspect there is a misconception that system 1 (intuitive) is mapped to the right brain and system 2 (deliberate) is mapped to the left brain.
The left brain is livewired to be competent in sequential thought while the right brain is livewired to be competent in parallel thought. One is egocentric and the other is allocentric. One is symbolic and the other is empathic.
One is reductionist and the other is holistic. One is noun-centric and the other is verb-centric. One emphasizes individuality and the other the collective. We can make many analogies about the dichotomy between the two hemispheres of the brain.