Sparse coding can quickly, accurately, and inexpensively represent the stimulus information received by biological vision neurons. However, there is no entire circuit that can realize real -time sparse coding by effic...
详细信息
Sparse coding can quickly, accurately, and inexpensively represent the stimulus information received by biological vision neurons. However, there is no entire circuit that can realize real -time sparse coding by efficient analog computation. A memristor neural network circuit that solves the sparse coding problem in real -time and in parallel is proposed to solve such a problem. In our circuit, a novel memristor array structure can realize both reading and writing in parallel. A neural network circuit that can execute the locally competitive algorithm (LCA) is designed based on this structure. Given these designs, the proposed neural networks circuit can utilize the programmability of the memristor array to real -time process various sparse coding problems. Based on the proposed circuit, the module can process binary and grayscale image sparse coding, providing a circuit implementation platform for sparse coding tasks. The simulation results demonstrate that the processing speed of sparse coding is improved compared with the MATLAB simulation and the application robustness is enhanced.
Gammachirp filterbank has been used to approximate the cochlea in sparse coding algorithms. An oriented grid search optimization was applied to adapt the gammachirp's parameters and improve the Matching Pursuit (M...
详细信息
ISBN:
(纸本)9781728163383
Gammachirp filterbank has been used to approximate the cochlea in sparse coding algorithms. An oriented grid search optimization was applied to adapt the gammachirp's parameters and improve the Matching Pursuit (MP) algorithm's sparsity along with the reconstruction quality. However, this combination of a greedy algorithm with a grid search at each iteration is computationally demanding and not suitable for real-time applications. This paper presents an adaptive approach to optimize the gammachirp's parameters but in the context of the locally competitive algorithm (LCA) that requires much fewer computations than MP. The proposed method consists of taking advantage of the LCA's neural architecture to automatically adapt the gammachirp's filterbank using the backpropagation algorithm. Results demonstrate an improvement in the LCA's performance with our approach in terms of sparsity, reconstruction quality, and convergence time. This approach can yield a significant advantage over existing approaches for real-time applications.
The locally competitive algorithm (LCA) is a continuous-time dynamical system designed to solve the problem of sparse approximation. This class of approximation problems plays an important role in producing state-of-t...
详细信息
ISBN:
(纸本)9781612842271
The locally competitive algorithm (LCA) is a continuous-time dynamical system designed to solve the problem of sparse approximation. This class of approximation problems plays an important role in producing state-of-the-art results in many signal processing and inverse problems, and implementing the LCA in analog VLSI may significantly improve the time and power necessary to solve these optimization programs. The goal of this paper is to analyze the dynamical behavior of the LCA system and guarantee its convergence and stability. We show that fixed points of the system are extrema of the sparse approximation objective function when designed for a certain class of sparsity-inducing cost penalty. We also show that, if the objective has a unique minimum, the LCA converges for any initial point. In addition, we prove that under certain conditions on the solution, the LCA converges in a finite number of switches (i.e., node threshold crossings).
Spike sorting is a crucial step in the analysis of multichannel neural signals that enables the identification of individual neurons' activity. However, the limited availability of low-power neuromorphic spike sor...
详细信息
Ear characteristic is a promising biometric modality that has demonstrated good biometric performance. In this paper, we investigate a novel and challenging problem to verify a subject (or user) based on the ear chara...
详细信息
Ear characteristic is a promising biometric modality that has demonstrated good biometric performance. In this paper, we investigate a novel and challenging problem to verify a subject (or user) based on the ear characteristics after undergoing ear surgery. Ear surgery is performed to reconstruct the abnormal ear structures both locally and globally to beautify the overall appearance of the ear. Ear surgery performed for both for beautification and corrections alters the original ear characteristics to the greater extent that will challenge the comparison and subsequently verification performance of the ear recognition systems. This work presents a new database of images from 211 subjects with surgically altered ear along with corresponding pre and post-surgery samples. We then propose a novel scheme for ear verification based on the features extracted using a bank of filters learnt using Topographic locally competitive algorithm (T-LCA) and comparison is carried out using Robust Probabilistic Collaborative Representation Classifier (R-ProCRC). Extensive experiments are carried out on both clean (normal) and surgically altered ear database to evaluate the performance of the proposed ear verification scheme. We also present a comprehensive performance analysis by comparing the performance of the proposed ear recognition scheme with eight different state-of-the-art ear verification system. Furthermore, we also present a new scheme to detect both deformed and surgically altered ear using one-class classification. Experimental results indicate the magnitude of problem in verifying the surgically altered ears and the signifies the need for considerable research in this direction. (C) 2018 Published by Elsevier Ltd.
We present an analysis of the locallycompetitive Algotihm (LCA), which is a Hopfield-style neural network that efficiently solves sparse approximation problems (e.g., approximating a vector from a dictionary using ju...
详细信息
We present an analysis of the locallycompetitive Algotihm (LCA), which is a Hopfield-style neural network that efficiently solves sparse approximation problems (e.g., approximating a vector from a dictionary using just a few nonzero coefficients). This class of problems plays a significant role in both theories of neural coding and applications in signal processing. However, the LCA lacks analysis of its convergence properties, and previous results on neural networks for nonsmooth optimization do not apply to the specifics of the LCA architecture. We show that the LCA has desirable convergence properties, such as stability and global convergence to the optimum of the objective function when it is unique. Under some mild conditions, the support of the solution is also proven to be reached in finite time. Furthermore, some restrictions on the problem specifics allow us to characterize the convergence rate of the system by showing that the LCA converges exponentially fast with an analytically bounded convergence rate. We support our analysis with several illustrative simulations.
BackgroundHistopathology images of tumor biopsies present unique challenges for applying machine learning to the diagnosis and treatment of cancer. The pathology slides are high resolution, often exceeding 1GB, have n...
详细信息
BackgroundHistopathology images of tumor biopsies present unique challenges for applying machine learning to the diagnosis and treatment of cancer. The pathology slides are high resolution, often exceeding 1GB, have non-uniform dimensions, and often contain multiple tissue slices of varying sizes surrounded by large empty regions. The locations of abnormal or cancerous cells, which may constitute a small portion of any given tissue sample, are not annotated. Cancer image datasets are also extremely imbalanced, with most slides being associated with relatively common cancers. Since deep representations trained on natural photographs are unlikely to be optimal for classifying pathology slide images, which have different spectral ranges and spatial structure, we here describe an approach for learning features and inferring representations of cancer pathology slides based on sparse *** show that conventional transfer learning using a state-of-the-art deep learning architecture pre-trained on ImageNet (RESNET) and fine tuned for a binary tumor/no-tumor classification task achieved between 85% and 86% accuracy. However, when all layers up to the last convolutional layer in RESNET are replaced with a single feature map inferred via a sparse coding using a dictionary optimized for sparse reconstruction of unlabeled pathology slides, classification performance improves to over 93%, corresponding to a 54% error *** conclude that a feature dictionary optimized for biomedical imagery may in general support better classification performance than does conventional transfer learning using a dictionary pre-trained on natural images.
This document provides a correction to the proof of the theorem establishing the exponential speed of convergence of the locally competitive algorithm (LCA) in the paper "Convergence and Rate Analysis of Neural N...
详细信息
This document provides a correction to the proof of the theorem establishing the exponential speed of convergence of the locally competitive algorithm (LCA) in the paper "Convergence and Rate Analysis of Neural Networks for Sparse Approximation."
We revisit herein the problem of time-difference-of-arrival (TDOA) based localization under the mixed line-of-sight/non-line-of-sight propagation conditions. Adopting the strategy of statistically robustifying the non...
详细信息
We revisit herein the problem of time-difference-of-arrival (TDOA) based localization under the mixed line-of-sight/non-line-of-sight propagation conditions. Adopting the strategy of statistically robustifying the non-outlier-resistant l(2) loss, we formulate it as the minimization of a possibly non-differentiable generalized robust cost function, which is rooted in the analog locally competitive algorithm (LCA) for sparse approximation. We then present a Lagrange programming neural network to address the optimization formulation, with the non-differentiability issues being handled by grafting thereon the LCA concept of internal state dynamics. Compared with the existing algorithms, our approach is computationally less expensive, less reliant on the use of a priori error information, and observed to be capable of producing higher localization accuracy.
Sparse codes for auditory stimuli are typically based on time-dependent power spectra. These spectrographic images result in the loss of phase information at fine temporal scales that could be useful for subsequent do...
详细信息
ISBN:
(纸本)9781467399197
Sparse codes for auditory stimuli are typically based on time-dependent power spectra. These spectrographic images result in the loss of phase information at fine temporal scales that could be useful for subsequent downstream processing tasks, such as monaural source separation. Using a resonance model of the human cochlea, we were able to learn spectrotemporal features on a sliding window of auditory images that allowed for phase rich reconstructions that remained accurate to millisecond scales. Moreover, we showed that such features exhibit tonotopy when trained on musical input and are useful in denoising. To our knowledge, this is the first demonstration of how sparsely activated auditory features that preserve phase information on time scales relevant to monaural source segmentation can be learned on streaming spectrotemporal auditory images.
暂无评论