Role of noises in neural networks

1995 ◽  
Vol 52 (6) ◽  
pp. 6593-6606 ◽  
Author(s):  
Sergio Albeverio ◽  
Jianfeng Feng ◽  
Minping Qian
Keyword(s):  
Neural Networks

Technique of scientific and technical forecasting using neural networks

2018 ◽  
pp. 103-110
Author(s):  
V. V. Nefedev
Keyword(s):  
Mathematical Modeling ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Original Method ◽  
Forecasting Methods ◽  
Expert Assessments ◽  
Artificial Neural

For the definition and implementation of breakthrough technologies the most important is the role of scientific and technical forecasting. Well-known forecasting methods based on extrapolation, expert assessments and mathematical modeling are not universal and have a number of significant disadvantages. The article proposes an original method of scientific and technical forecasting based on the use of the methodology of artificial neural networks. 

The Role of Regularization in Overparameterized Neural Networks*

2020 ◽  
Author(s):  
Siddhartha Satpathi ◽  
Harsh Gupta ◽  
Shiyu Liang ◽  
R Srikant
Keyword(s):  
Neural Networks

The Main Sequence of Human Optokinetic Afternystagmus (OKAN)

2009 ◽  
Vol 101 (6) ◽  
pp. 2889-2897 ◽  
Author(s):  
Andre Kaminiarz ◽  
Kerstin Königs ◽  
Frank Bremmer
Keyword(s):  
Neural Networks ◽  
Eye Movements ◽  
Main Sequence ◽  
Critical Role ◽  
Saccade Target ◽  
Control Mechanisms ◽  
Visually Guided ◽  
Background Characteristics ◽  
Optokinetic Afternystagmus

Different types of fast eye movements, including saccades and fast phases of optokinetic nystagmus (OKN) and optokinetic afternystagmus (OKAN), are coded by only partially overlapping neural networks. This is a likely cause for the differences that have been reported for the dynamic parameters of fast eye movements. The dependence of two of these parameters—peak velocity and duration—on saccadic amplitude has been termed “main sequence.” The main sequence of OKAN fast phases has not yet been analyzed. These eye movements are unique in that they are generated by purely subcortical control mechanisms and that they occur in complete darkness. In this study, we recorded fast phases of OKAN and OKN as well as visually guided and spontaneous saccades under identical background conditions because background characteristics have been reported to influence the main sequence of saccades. Our data clearly show that fast phases of OKAN and OKN differ with respect to their main sequence. OKAN fast phases were characterized by their lower peak velocities and longer durations compared with those of OKN fast phases. Furthermore we found that the main sequence of spontaneous saccades depends heavily on background characteristics, with saccades in darkness being slower and lasting longer. On the contrary, the main sequence of visually guided saccades depended on background characteristics only very slightly. This implies that the existence of a visual saccade target largely cancels out the effect of background luminance. Our data underline the critical role of environmental conditions (light vs. darkness), behavioral tasks (e.g., spontaneous vs. visually guided), and the underlying neural networks for the exact spatiotemporal characteristics of fast eye movements.

scholarly journals Understanding the drivers of marine liquid-water cloud occurrence and properties with global observations using neural networks

2017 ◽  
Author(s):  
Hendrik Andersen ◽  
Jan Cermak ◽  
Julia Fuchs ◽  
Reto Knutti ◽  
Ulrike Lohmann
Keyword(s):  
Neural Networks ◽  
Liquid Water ◽  
Meteorological Parameters ◽  
Reanalysis Data ◽  
Main Determinant ◽  
Boundary Layer Height ◽  
Water Cloud ◽  
Aerosol Cloud Interactions ◽  
Water Amount

Abstract. The role of aerosols, clouds and their interactions with radiation remain among the largest unknowns in the climate system. Even though the processes involved are complex, aerosol-cloud interactions are often analyzed by means of bivariate relationships. In this study, 15 years (2001–2015) of monthly satellite-retrieved nearly-global aerosol products are combined with reanalysis data of various meteorological parameters to predict satellite-derived marine liquid-water cloud occurrence and properties by means of regionally-specific artificial neural networks. The statistical models used are shown to be capable of predicting clouds, especially in regions of high cloud variability. At this monthly scale, lower tropospheric stability is shown to be the main determinant of cloud fraction and droplet size, especially in stratocumulus regions, while boundary layer height controls the liquid-water amount and thus the optical thickness of clouds. While aerosols show the expected impact on clouds, at this scale they are less relevant than some meteorological factors. Global patterns of the derived sensitivities point to regional characteristics of aerosol and cloud processes.

scholarly journals Project Selection Frameworks and Methodologies for Reducing Risks in Project Portfolio Management

2017 ◽  
pp. 245-263
Author(s):  
Fabio Nonino
Keyword(s):  
Neural Networks ◽  
Portfolio Management ◽  
Success Factors ◽  
Project Selection ◽  
Project Portfolio ◽  
Project Portfolio Management ◽  
Critical Success ◽  
Innovative Methodology ◽  
Correct Level

Extracting and consolidating knowledge from past projects can help managers in selecting projects with the correct level of riskiness, while market analysis gives directions for reaching the objective of a balanced project portfolio. To this extent, the chapter discusses strategic importance of project selection and the role of risks and uncertainties in project portfolio management and presents some fundamental and innovative frameworks and project selection methodologies for balancing risks. Finally, the chapter proposes a model containing an innovative methodology, based on artificial neural networks, to help managers in balancing project portfolio and assessing projects during the selection phase on the basis of risks, uncertainties and critical success factors.

scholarly journals The Interplay of Knowledge Representation with Various Fields of Artificial Intelligence in Medicine

2019 ◽  
Vol 28 (01) ◽  
pp. 027-034 ◽  
Author(s):  
Laszlo Balkanyi ◽  
Ronald Cornet
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Fuzzy Logic ◽  
Knowledge Representation ◽  
Expert Systems ◽  
Frequency Analysis ◽  
Medical Subject Headings ◽  
Subject Headings

Introduction: Artificial intelligence (AI) is widespread in many areas, including medicine. However, it is unclear what exactly AI encompasses. This paper aims to provide an improved understanding of medical AI and its constituent fields, and their interplay with knowledge representation (KR). Methods: We followed a Wittgensteinian approach (“meaning by usage”) applied to content metadata labels, using the Medical Subject Headings (MeSH) thesaurus to classify the field. To understand and characterize medical AI and the role of KR, we analyzed: (1) the proportion of papers in MEDLINE related to KR and various AI fields; (2) the interplay among KR and AI fields and overlaps among the AI fields; (3) interconnectedness of fields; and (4) phrase frequency and collocation based on a corpus of abstracts. Results: Data from over eighty thousand papers showed a steep, six-fold surge in the last 30 years. This growth happened in an escalating and cascading way. A corpus of 246,308 total words containing 21,842 unique words showed several hundred occurrences of notions such as robotics, fuzzy logic, neural networks, machine learning and expert systems in the phrase frequency analysis. Collocation analysis shows that fuzzy logic seems to be the most often collocated notion. Neural networks and machine learning are also used in the conceptual neighborhood of KR. Robotics is more isolated. Conclusions: Authors note an escalation of published AI studies in medicine. Knowledge representation is one of the smaller areas, but also the most interconnected, and provides a common cognitive layer for other areas.

Sign in / Sign up

Export Citation Format

Share Document