The Effect of Floating Wetland on Water Quality Improvement in a Eutrophic Lake.

Abstract

The study of the expressive power of neural networks has investigated the fundamental limits of neural networks. Most existing results assume real-valued inputs and parameters as well as exact operations during the evaluation of neural networks. However, neural networks are typically executed on computers that can only represent a tiny subset of the reals and apply inexact operations. In this work, we analyze the expressive power of neural networks under a more realistic setup: when we use floating-point numbers and operations. Our first set of results assumes floating-point operations where the significand of a float is represented by finite bits but its exponent can take any integer value. Under this setup, we show that neural networks using a binary threshold unit or ReLU can memorize any finite input/output pairs and can approximate any continuous function within a small error. We also show similar results on memorization and universal approximation when floating-point operations use finite bits for both significand and exponent; these results are applicable to many popular floating-point formats such as those defined in the IEEE 754 standard (e.g., 32-bit single-precision format) and bfloat16.

Control of Nuisance Cyanobacteria in Drinking Water Resources Using Alternative Algae-Blocking Mats

“…South Korea has been witnessed a similar situation. Eutrophication is rapidly spreading in many rivers and lakes, of which 72% are mesotrophic and 22% are eutrophic, with cyanobacteria blooms occurring from summer to winter [7]. Paldangho Lake, which is a major raw water source for over 20 million residents in Seoul and Gyeonggi, is also experiencing rapid eutrophication and resulting frequent cyanobacterial blooms due to its large drainage area and a constant inflow of domestic sewage, agricultural effluent, and livestock wastewater [8].…”