24 papers · ranked by Valyu relevance
Misha Denil, Nando de Freitas
It has recently been observed that certain extremely simple feature encoding techniques are able to achieve state of the art performance on several standard image classification benchmarks including deep belief networks, convolutional nets, factored RBMs, mcRBMs, convolutional RBMs, sparse autoencoders and several…
Yanbo Lian, Anthony N. Burkitt
Sparse coding, predictive coding and divisive normalization have each been found to be principles that underlie the function of neural circuits in many parts of the brain, supported by substantial experimental evidence. However, the connections between these related principles are still poorly understood. In this…
Michael Beyeler, Emily L. Rounds, Kristofor D. Carlson, Nikil Dutt + 2 more
'Jeffrey L. Krichmar' 'Aldo A. Faisal'] Supported by recent computational studies, there is increasing evidence that a wide range of neuronal responses can be understood as an emergent property of nonnegative sparse coding (NSC), an efficient population coding scheme based on dimensionality reduction and sparsity…
Yanbo Lian, Anthony N. Burkitt, Boris S. Gutkin
Sparse coding, predictive coding and divisive normalization have each been found to be principles that underlie the function of neural circuits in many parts of the brain, supported by substantial experimental evidence. However, the connections between these related principles are still poorly understood. Sparse coding…
Yanbo Lian, Anthony N. Burkitt
Experimental studies of grid cells in the Medial Entorhinal Cortex (MEC) have shown that they are selective to an array of spatial locations in the environment that form a hexagonal grid. However, place cells in the hippocampus are only selective to a single-location of the environment while granule cells in the…
Yuwei Cui, Subutai Ahmad, Jeff Hawkins
Hierarchical temporal memory (HTM) provides a theoretical framework that models several key computational principles of the neocortex. In this paper, we analyze an important component of HTM, the HTM spatial pooler (SP). The SP models how neurons learn feedforward connections and form efficient representations of the…
Damien Drix, Verena V. Hafner, Michael Schmuker
Cortical neurons are silent most of the time. This sparse activity is energy efficient, and the resulting neural code has favourable properties for associative learning. Most neural models of sparse coding use some form of homeostasis to ensure that each neuron fires infrequently. But homeostatic plasticity acting on a…
Bailey Kong, Charless C. Fowlkes
In this paper, we explore an efficient variant of convolutional sparse coding with unit norm code vectors where reconstruction quality is evaluated using an inner product (cosine distance). To use these codes for discriminative classification, we describe a model we term Energy-Based Spherical Sparse Coding (EB-SSC) in…
Peter Loxley
Sparse codes in neuroscience have been suggested to offer certain computational advantages over other neural representations of sensory data. To explore this viewpoint, a sparse code is used to represent natural images in an optimal control task solved with neuro-dynamic programming, and its computational properties…
Eva L Dyer, Ueli Rutishauser, Richard G Baraniuk
Degeneracy is a ubiquitous feature of computation and coding in biological systems. Degenerate codes-codes in which multiple code words have the same meaning or interpretation-arise in a wide range of biological processes, from the many-to-one mapping of codons to amino acids to the numerous instances of degenerate…
Michael Beyeler, Emily Rounds, Kristofor D. Carlson, Nikil Dutt + 1 more
Supported by recent computational studies, sparse coding and dimensionality reduction are emerging as a ubiquitous coding strategy across brain regions and modalities, allowing neurons to achieve nonnegative sparse coding (NSC) by efficiently encoding high-dimensional stimulus spaces using a sparse and parts-based…
Jonathan J. Hunt, Peter Dayan, Geoffrey J. Goodhill, Matthias Bethge
Receptive fields acquired through unsupervised learning of sparse representations of natural scenes have similar properties to primary visual cortex (V1) simple cell receptive fields. However, what drives in vivo development of receptive fields remains controversial. The strongest evidence for the importance of sensory…
Joshua Bowren, Luis Gonzalo Sánchez-Giraldo, Odelia Schwartz
Sparse coding has been incorporated in models of the visual cortex for its computational advantages and connection to biology. But how the level of sparsity contributes to performance on visual tasks is not well understood. In this work, sparse coding has been integrated into an existing hierarchical V2 model (Hosoya…
Andrew Ligeralde, Michael R. DeWeese
It is well known that sparse coding models trained on natural images learn basis functions whose shapes resemble the receptive fields (RFs) of simple cells in the primary visual cortex (V1). However, few studies have considered how these basis functions develop during training. In particular, it is unclear whether…
Eric McVoy Dodds, Michael Robert DeWeese
Sparse coding models of natural images and sounds have been able to predict several response properties of neurons in the visual and auditory systems. While the success of these models suggests that the structure they capture is universal across domains to some degree, it is not yet clear which aspects of this…
Jianing V. Shi, Jim Wielaard, R. Theodore Smith, Paul Sajda
Sparse coding has been posited as an efficient information processing strategy employed by sensory systems, particularly visual cortex. Substantial theoretical and experimental work has focused on the issue of sparse encoding, namely how the early visual system maps the scene into a sparse representation. In this paper…
Walt Woods, Christof Teuscher
—Memristive crossbars have become a popular means for realizing unsupervised and supervised learning techniques. In previous neuromorphic architectures with leaky integrate-andfire neurons, the crossbar itself has been separated from the neuron capacitors to preserve mathematical rigor. In this work, we sought to…
Laurent Perrinet
``` @inbook{Perrinet15sparse, Author = {Perrinet, Laurent U.}, Chapter = {Sparse models for Computer Vision}, Citeulike-Article-Id = {13514904}, Editor = {Crist{\'{o}}bal, Gabriel and Keil, Matthias S. and Perrinet, Laurent U.}, Keywords = {bicv-sparse, sanz12jnp, vacher14}, month = nov, chapter = {14}, Priority = {0}…
Andrew P. Magyar
Single unit recordings in the human medial temporal lobe (MTL) have revealed a population of cells with conceptually based, highly selective activity, indicating the presence of a sparse neural code. Building off previous work by the author and J.C. Collins, this paper develops a statistical model for analyzing this…
S. Amin Moosavi, Antonia Pastor, Alfredo G. Ornelas, Elaine Tring + 1 more
Sparse coding enables cortical populations to represent sensory inputs efficiently, yet its temporal dynamics remain poorly understood. Consistent with theoretical predictions, we show that stimulus onset triggers broad cortical activation, initially reducing sparseness and increasing mutual information. Subsequently…
Sanjar Adilov
Machine learning models for molecular-property prediction typically work with molecular representations in the form of fingerprints, descriptors, or graphs. In case of fingerprints and descriptors, molecular representations usually comprise thousands of features, which causes the curse of dimensionality for many…
Kelsey Hatzell, Yanjie Zheng
X-ray Computed Tomography (CT) is a non-invasive, non-destructive approach to imaging materials, material systems and engineered components in two- and three- dimensions. Acquisition of 3D images requires the collection of hundreds or thousands of through-thickness X-ray radiographic images from different angles. Such…
Authors not listed
Real-world datasets in chemical engineering and bioengineering processes--such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials--can often be unlabelled or disorganized, rendering the training of existing supervised learning models ineffective at learning the…
Hasan M. Sayeed, Sterling G. Baird, Taylor D. Sparks
Capturing structure-property relationships of materials for property prediction using machine learning requires the representation or featurization of the structural aspects of materials at different levels, including atomic, crystal, and microscales. While crystal structure-based modeling techniques are effective for…