Neural correlates of sparse coding and dimensionality reduction
نویسندگان
چکیده
منابع مشابه
Sparse Unsupervised Dimensionality Reduction Algorithms
Principal component analysis (PCA) and its dual—principal coordinate analysis (PCO)—are widely applied to unsupervised dimensionality reduction. In this paper, we show that PCA and PCO can be carried out under regression frameworks. Thus, it is convenient to incorporate sparse techniques into the regression frameworks. In particular, we propose a sparse PCA model and a sparse PCO model. The for...
متن کاملFast, Deterministic and Sparse Dimensionality Reduction
We provide a deterministic construction of the sparse JohnsonLindenstrauss transform of Kane & Nelson (J.ACM 2014) which runs, under a mild restriction, in the time necessary to apply the sparse embedding matrix to the input vectors. Specifically, given a set of n vectors in R and target error ε, we give a deterministic algorithm to compute a {−1, 0, 1} embedding matrix of rank O((lnn)/ε) with ...
متن کاملDimensionality Reduction for Sparse and Structured Matrices
Dimensionality reduction has become a critical tool for quickly solving massive matrix problems. Especially in modern data analysis and machine learning applications, an overabundance of data features or examples can make it impossible to apply standard algorithms efficiently. To address this issue, it is often possible to distill data to a much smaller set of informative features or examples, ...
متن کاملRandom Dimensionality Reduction and Sparse Recovery Algorithms
We start by presenting the optimal dimensionality and complexity properties of an abstract codingdecoding system. The coding of high-dimensional vectors in R is performed by means of a linear map into a lower dimensional space R, where m ≪ N , and the decoding is performed by means of any nonlinear map with an error proportional to the best k-term approximation. Then we will show that such an i...
متن کاملDimensionality Reduction with Simultaneous Sparse Approximations
We propose a dimensionality reduction method for structured signals and its application in classification. The training phase implements a learning process that forms a parts-based representation of signals. Signals are jointly represented in a common subspace extracted from a redundant dictionary of basis functions, using greedy pursuit algorithms for simultaneous sparse approximations. A smal...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: PLOS Computational Biology
سال: 2019
ISSN: 1553-7358
DOI: 10.1371/journal.pcbi.1006908