Pattern Classification

By Katherine L. Silversides. 2021

The computational neural-network structures described in the literature are often based on the concept of linear neural units (LNUs). The biological neuron is a complex computing element, which performs more computations than just linear summation. The computational efficiency of the neural network depends on its structure and the training methods employed. Higher-order combinations of inputs and weights will yield higher neural performance. In this paper, a quadratic-neural unit (QNU) has been developed using a novel general matrix form of the quadratic operation. We have used the QNU for realizing different logic circuits.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Security Evaluation of Support Vector Machines in Adversarial Environments (2014, background): “The adversary’s knowledge of the attacked system can be defined based on the main components involved in the design of a machine learning system, as described in [29] and depicted in Figure 3.”
Supervised probabilistic principal component analysis (2006, background): “Linear discriminant analysis (LDA) focuses on multi-class classification and finds projection directions that separate the data best (see [4]).”
Building a Dynamic Reputation System for DNS (2010, methodology): “19 EXP [6] 09-22 1165651291.”
Towards comprehensive support for organizational mining (2008, methodology): “To derive a hierarchical organizational model, we apply AHC (Agglomerative Hierarchical Clustering) technique [12].”
Convergence Rates of the POD–Greedy Method (2013, methodology): “The crucial ingredient for time-sequence compression is the use of a principal component analysis (PCA) [3,11] of the snapshots’ Grammian matrix.”
Document clustering using locality preserving indexing (2005, methodology): “Note that, an upper bound of the number of non-zero eigenvalues of LDA is k − 1 where k is the number of classes, please see [10] for details.”
Introspective Neural Networks for Generative Modeling (2017, methodology): “Popular unsupervised learning methods include mixture models [9], principal component analysis (PCA) [24], spectral clustering [38], topic modeling [4], and autoencoders [3, 2].”