Skip to content

Latest commit

 

History

History
29 lines (24 loc) · 1.71 KB

BrainTheories.md

File metadata and controls

29 lines (24 loc) · 1.71 KB
Raw

Brain Theories Numbered By Importance

  1. One learning algorithm in the neocortex of the brain

    • Support:
      • google "Roe et al., 1992"
        • Summary: If you cut the wires from the ear to the auditory cortex and rewire the optic nerve to the auditory cortex, then the auditory cortex learns to see.
      • google "Metin & Frost, 1989"
        • Summary: If you make the wires from the optic nerve connect to the somatosensory cortex then the somatosensory cortex learns to see.
    • Reasoning: If different parts of the neocortex (contains auditory cortex, somatosensory, and others..) can be given new input and learn to process this new input, then we can guess there is a single learning algorithm in all parts of the neocortex.

  2. Information flow in Brain

    • Support:
    • synapseOnAxonOfNeuronA -> dendriteOfNeuronB -> cellBodyOfNeuronB -> axonOfNeuronB -> synapseOfNeuronC

  3. The majority of what we call intelligence is developed during the first 2 years of life

    • Support:
    • Reasoning: About 10^14 synapses in the brain by 2 years of age. About 10^8 seconds in 2 years. That means about 10^6 synapses are formed per second in a fetus and infant.

  4. Consciousness partially exists through the LIMITED neural circuits for smell. Does olfaction pass through the thalamus?

  5. Spatial Pooling efficiently stores sensory information as the activation of a fixed set of neurons in sequence in a hierarchy.

    • Support:
    • Experimental Data:

  6. After you change your password it takes about 5 bad predictions over time to fix your habit. This is directly tied to changing synapse permanence increase and decrease rate based on # of cells incorrectly predicted.