First Principles
Are there any concepts that could be of use in suggesting how machine learning could understand and convey meaning?
I think there are: repetition and generalization.
I may be wrong about this. In the words of the great Philosopher Charles Barkley, I may be wrong, but I doubt it.
I think perception and learning work in this way. It doesn’t really matter if this is actually the exact mechanism for perception and learning; what matters is that this idea can lead to discoveries about how we might teach a machine to learn.
If you think about looking at any specific object, whether it’s a geranium, a cherry tree, or a cow named Buttercup, you’ve never actually seen it from this precise angle and at this precise distance before. Yet you recognize it as Buttercup.
This lack of precision, this kind of fuzzy perception, is the norm, and is necessary for us to survive in the world. The brain is not a perfect precise detail-memorizing machine; there are an infinite number of details. What we are seeing when we see Buttercup is a recognizable generalization of that very specific cow. There are many other cows; she is one. Buttercup herself is specific; our perception of her is a generalization (in computer terms, it is an abstraction — abstracted out from the instance). This is true of everything we see; it is well known in psychology as perceptual constancy.
What this means is that we live in a world of specifics, but we perceive a world of generalities. In computer terms, we live in a world of instances but we perceive that world as a world of classes. The generalizations themselves are what we ‘understand,’ which is to say, what we recognize.
It is not surprising then, that the process of convolving in a convolutional neural network involves averaging, recalculating the value for a given pixel or set of pixels.
What that in turn means, is this: recognition is composed of repetition and generalization. Or, in pseudo-mathematical terms, recognition = repetition + generalization. That is what machine learning does.
The question, moving forward, will be: how clever can we be in steering a model toward increasingly abstract levels? It is our human ability to recognize previously unknown items or concepts, as comprehensible variations on what we have already known.