Sparsey: Event Recognition Via Deep Hierarchical Spare Distributed Codes

Abstract

Visual cortex's hierarchical, multi-level organization is captured in many biologically inspired computational vision models, the general idea being that progressively larger scale, more complex spatiotemporal features are represented in progressively higher areas. However, most earlier models use localist representations (codes) in each representational field, which we equate with the cortical macrocolumn (mac), at each level. In localism, each represented feature/event (item) is coded by a single unit. Our model, Sparsey, is also hierarchical but crucially, uses sparse distributed coding (SDC) in every mac in all levels. In SDC, each represented item is coded by a small subset of the mac's units. SDCs of different items can overlap and the size of overlap between items can represent their similarity. The difference between localism and SDC is crucial because SDC allows the two essential operations of associative memory, storing a new item and retrieving the best-matching stored item,

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keyrinkus2016sparsey

Related papers

• Efficient Similarity-preserving Unsupervised Learning Using Modular Sparse Distributed Codes And Novelty-contingent Noise (2020)0.00
• Beyond Matryoshka: Revisiting Sparse Coding For Adaptive Representation (2025)4.30
• Multi-view Task-driven Recognition In Visual Sensor Networks (2017)4.52
• Learning Visual Hierarchies In Hyperbolic Space For Image Retrieval (2024)0.00
• Achieving Fine-grained Cross-modal Understanding Through Brain-inspired Hierarchical Representation Learning (2026)0.00
• Associative Memories Via Predictive Coding (2021)0.00
• Classification And Generation Of Real-world Data With An Associative Memory Model (2022)6.77
• Delving Deeper: Hierarchical Visual Perception For Robust Video-text Retrieval (2026)1.24