paper-with-me

Papers

Structured sparse coding via lateral inhibition

2011-12-01 · NeurIPS 2011 12 · Arthur D. Szlam, Karol Gregor, Yann L. Cun

This work describes a conceptually simple method for structured sparse coding and dictionary design. Supposing a dictionary with K atoms, we introduce a structure as a set of penalties or interactions between every pair of atoms. We describe modifications of standard sparse coding algorithms for inference in this setting, and describe experiments showing that these algorithms are efficient. We show that interesting dictionaries can be learned for interactions that encode tree structures or locally connected structures. Finally, we show that our framework allows us to learn the values of the interactions from the data, rather than having them pre-specified.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sparse Code Formation with Linear Inhibition

2015-03-13 · Nam Do-Hoang Le

Sparse code formation in the primary visual cortex (V1) has been inspiration for many state-of-the-art visual recognition systems. To stimulate this behavior, networks are trained networks under mathematical constraint o…

Inhibition in Random Neuronal Networks Enhances Response Variability and Disrupts Stimulus Discrimination

2018-09-15

Inhibition is considered to shape neural activity, and broaden its pattern repertoire. In the sensory organs, where the anatomy of neural circuits is highly structured, lateral inhibition sharpens contrast among stimulus…

AnatomyBlocking

Convolutional Sparse Coding via the Locally Competitive Algorithm on Loihi 2

2026-06-07 · Geoffrey Kasenbacher, Daniel Ruepp, Gerrit A. Ecke arxiv

Sparse coding provides a principled framework for signal representation by expressing an input as a linear combination of only a small number of basis functions. The Locally Competitive Algorithm (LCA) is particularly at…

Emergence of robust looming selectivity via coordinated inhibitory neural computations

2025-10-01 · Qinbing Fu, Ziyan Qin arxiv

In the locust's lobula giant movement detector neural pathways, four categories of inhibition, i.e., global inhibition, self-inhibition, lateral inhibition, and feed-forward inhibition, have been functionally explored in…

Improved Training of Sparse Coding Variational Autoencoder via Weight Normalization

2021-01-23 · Linxing Preston Jiang, Luciano de la Iglesia

Learning a generative model of visual information with sparse and compositional features has been a challenge for both theoretical neuroscience and machine learning communities. Sparse coding models have achieved great s…

Decoder