Bucketed PCA Neural Networks with Neurons Mirroring Signals

  title={Bucketed PCA Neural Networks with Neurons Mirroring Signals},
  author={Jackie Shen},
  • Jackie Shen
  • Published 2 August 2021
  • Computer Science
  • ArXiv
The bucketed PCA neural network (PCA-NN) with transforms is developed here in an effort to benchmark deep neural networks (DNN’s), for problems on supervised classification. Most classical PCA models apply PCA to the entire training data set to establish a reductive representation and then employ non-network tools such as high-order polynomial classifiers. In contrast, the bucketed PCA-NN applies PCA to individual buckets which are constructed in two consecutive phases, as well as retains a… 

Figures from this paper



Deep Learning

Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.

Receptive fields of single neurones in the cat's striate cortex

The present investigation, made in acute preparations, includes a study of receptive fields of cells in the cat's striate cortex, which resembled retinal ganglion-cell receptive fields, but the shape and arrangement of excitatory and inhibitory areas differed strikingly from the concentric pattern found in retinalganglion cells.

A Multifont Word Recognition System for Postal Address Reading

  • Schurmann
  • Computer Science
    IEEE Transactions on Computers
  • 1978
The basic design principles of a multifont word recognition system developed for postal address reading are described, with a multiple-channel/multiple-choice approach taken in designing the overall system.

An Introduction to Linear Algebra

Class notes on vectors, linear combination, basis, span. 1 Vectors Vectors on the plane are ordered pairs of real numbers (a, b) such as (0, 1), (1, 0), (1, 2), (−1, 1). The plane is denoted by R,

Image processing and analysis - variational, PDE, wavelet, and stochastic methods

The author’s research focused on image modeling and representation, which focused on the representation of black-and-white images through the lens of a discrete-time model.

Filtering, Segmentation and Depth

The 2.1D sketch was found by filtering for occlusion detection and finding contours and junctions and finding the 2.2D sketch by following the dotted line pattern.

What is Pattern Theory

Linear Algebra and Learning from Data

  • Wellesley-Cambridge Press,
  • 2019

Construction of quadratic polynomial classifiers

  • Proc. Int’l Conf. Pattern Recog., pages 161–165,
  • 1976