Home » Neuroscience Research » Research Publications » Posters
This poster explains HTM Sequence Memory, a neural mechanism for sequence learning, which is ubiquitous in the cortex and has the following characteristics: 1) neurons learn to recognize patterns; 2) pattern recognition acts as predictions; 3) a neuron network forms a sequence memory, and 4) sparse presentations lead to robust recognition.
This poster introduces a theory of sequence memory in the neocortex called HTM Sequence Memory. The three characteristics of HTM Sequence Memory are: 1) Neurons learn to recognize hundreds of patters; 2) Pattern recognition acts as predictions; and 3) a network of neurons forms a powerful sequence memory.
How can the cortex build a sensorimotor model of the world? First, we propose a biologically detailed model of sensorimotor inference. Then, we build a model with a premise that predictable transitions lead to invariant representations. We then tested the model, measuring neuron activations over time.