NENCDec 28, 2015

Approximate Hubel-Wiesel Modules and the Data Structures of Neural Computation

arXiv:1512.08457v12 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of understanding neural computation across brain regions for researchers in neuroscience and AI, offering a unified perspective on perception and memory.

The paper tackles the problem of modeling the interface between perception and memory by proposing a framework that unifies view-dependent and invariant visual processing with episodic memory effects, expanding existing two-speed learning theories to cover the entire pathway from V1 to hippocampus.

This paper describes a framework for modeling the interface between perception and memory on the algorithmic level of analysis. It is consistent with phenomena associated with many different brain regions. These include view-dependence (and invariance) effects in visual psychophysics and inferotemporal cortex physiology, as well as episodic memory recall interference effects associated with the medial temporal lobe. The perspective developed here relies on a novel interpretation of Hubel and Wiesel's conjecture for how receptive fields tuned to complex objects, and invariant to details, could be achieved. It complements existing accounts of two-speed learning systems in neocortex and hippocampus (e.g., McClelland et al. 1995) while significantly expanding their scope to encompass a unified view of the entire pathway from V1 to hippocampus.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes