Neuroscience bits from my research: Recognition is a by-product of perception.
Nothing can move in more than one direction at the same time.
Don't let its simplicity fool you. I believe this is the most powerful principle of perception in the visual cortex. It is used for both learning and on-the-fly perception.
While researching the visual system of the human brain, I came to understand that, unlike deep neural nets, the visual cortex doesn't learn to recognize patterns, scenes or objects. Rather, it learns to perceive the world instantly, i.e., to use the world as its own model.
Recognition is a by-product of perception. When a perceptual representation is built in memory, it has a short life and, unless rehearsed (recalled) repeatedly, it slowly decays and disappears.
The advantage of universal and instantaneous perception is that the brain is not blind to patterns or scenes it has not encountered before. Humans learn to achieve universal perception during the first few years after birth. During this time, most of the initial connections in the cortex disappear.
Instant perception solves the edge case problem, the bane of the self-driving car industry. This is an absolutely essential ability that deep learning systems do not have. It is one of the many reasons that DL will not be part of the AGI solution.
I believe there are maybe 2 or 3 additional principles that govern visual perception. I have a couple of partly baked ideas percolating in my brain. Hopefully, something will come out of it soon.
My thesis is that all the sensory modalities are analogous. The main difference is in the architecture and function of the various sensors. This is exciting because it means that solving one cortical functionality amounts to solving all the others.
Concept formation, including language learning, is a separate process that uses recognized percepts from all the regions of the cortex to form associations. It's an essential part of intelligence but I think it's a trivial problem compared to sensory perception.
I could be wrong but I still believe that the mystery of intelligence will likely be solved before the end of this decade. It will be a neuroscience solution. Work in progress.
I love the brain. 🧠😍
Neuroscience bits from my research: Neuroscience and Isaac Newton
Progress annoucement
I'm a fanatical believer in Occam's razor. It is one of the reasons that I admire Isaac Newton. He took an absolute mess of experimental data carefully accumulated over many centuries and reduced them to a single equation for the force of gravity. It was a tour de force. I believe that the same can be done for various aspects of intelligence in the brain.
I study the visual system of the human brain, which includes the retina, the thalamus (LGN) and the visual cortex. I have always believed that vision is governed by a few simple principles. Most of my research consists of trying to flesh them out of the available data.
I'm now convinced that perceptual learning in the visual cortex may turn out to be much simpler than even I anticipated. 😯
The human retina is a not a pixel sensor. It consists of a huge number of tiny edge movement detectors called retinal ganglion cells or RGCs. The human retina can detect movements in 10 orientations and 20 directions (2 per orientation). My thesis is that the foundation of visual perception is governed by a deceptively simple but powerful principle:
Nothing can move in more than one direction at the same time.
Perceptual learning is almost entirely about the elimination of timing contradictions. All the information needed is in the sensory stream. There is no use for error backpropagation, gradient descent, connection weights or function optimization. No problem of overfitting or getting stuck in local optima either. It's a beautiful thing. 🤔
I can't say more. Work in progress. I love the brain. 🧠😍