摘要
This paper pursues part of a theory to understand sequence prediction networks that use local context neuron encodings. In particular, a previously described neural network model of hippocampal CA3 is studied. General expressions relating CA3 interpattern distances (which reflect local context codes) to sequence length memory capacity are created and verified by computer simulations. As a result, we confirm a very simple relationship between the sequence length memory capacity and a combination of average activity level and the average local context lifetimes. Sequence length memory capacity is also bounded for networks using such local context neuronal codes. Thus, this simple theory quantifies an important limitation on a fully adaptive (i.e. self-supervising) neural model capable of creating context-dependent learning and memory.
学科与关键词
- Memory capacity for sequences in a recurrent network with biological constraintsLeibold, C; Kempter, RNeural Computation, 2006, 18(4): 904-941.被引 46
- Context codes and the effect of noisy learning on a simplified hippocampal CA3 modelWu, XB; Baxter, RA; Levy, WBBiological Cybernetics, 1996, 74(2): 159-165.被引 36
- Storage fidelity for sequence memory in the hippocampal circuitBayati, Mehdi; Neher, Torsten; Melchior, Jan; Diba, Kamran; Wiskott, Laurenz; Cheng, Sen*PLoS One, 2018, 13(10): e0204685.被引 6
