Cascade Networks, Generalized Neural Networks, and Approximation of Functions
Sordillo, Diana C.
0000-0001-8463-9490
:
2022-06-21
Abstract
A neural network is a supervised machine learning model based on how the brain acquires and stores knowledge. Due to the availability of large amounts of training data and improvements in computing power, neural networks are increasingly used in a wide range of machine learning problems. While neural networks have produced an abundance of successes in practical applications, the basis of these successes lacks rigorous mathematical analysis. In its most general form, a neural network is a function given by repeatedly applying a fixed function, in general nonlinear, to an affine operator. In this thesis, close analogs to neural networks using the rectified linear unit (ReLU) activation function are introduced. These analogs, called cascade networks, are also functions given by repeatedly applying a fixed function to an affine operator. Cascade networks have a close connection with algorithms used in computer aided geometric design and multiresolution analysis. In particular, the connection between cascade networks, subdivision algorithms, and the cascade algorithm is discussed. Using cascade networks to approximate polynomials and smooth functions, similar results were obtained when compared to the results for ReLU neural networks.
Files in this item
This item appears in the following collection(s):
Related items
Showing items related by title, author, creator and subject.
-
Hong, Sunghoon (2012-04-17)Department: EconomicsMy research on the economics of network flows is motivated by (i) the possibility of bads being carried through networks, together with goods, (ii) the analysis of strategic behavior of agents in networks, and (iii) the ...
-
Patil, Prithviraj Pradiprao (2016-07-22)Department: Computer ScienceSoftware Defined Networking (SDN) has seen growing deployment in the large wired data center networks due to its advantages like better network manageability and higher-level abstractions. At the core of SDN is the separation ...
-
Devkota, Tina (2009-03-27)Department: Computer ScienceEmerging applications in the realm of Intelligent Transportation systems, such as traffic congestion management and vehicle rerouting, weather alerts, and infotainment via multimedia streaming, require timely and reliable ...