The Fisher information matrix of a multi-layer perceptron network can be singular at certain parameters, and in such cases many statistical techniques based on asymptotic theory cannot be applied properly. In this paper, we prove rigorously that the Fisher information matrix of a three-layer perceptron network is positive definite if and only if the network is irreducible; that is, if there is no hidden unit that makes no contribution to the output and there is no pair of hidden units that could be collapsed to a single unit without altering the input-output map. This implies that a network that has a singular Fisher information matrix can be reduced to a network with a positive definite Fisher information matrix by eliminating redundant hidden units. Copyright 1996 Elsevier Science Ltd
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/0893-6080(95)00119-0 | DOI Listing |
Biotechnol Bioeng
January 2025
Boehringer Ingelheim Pharma GmbH & Co.KG, Biopharmaceuticals Germany, Biberach an der Riß, Germany.
Process models are increasingly used to support upstream process development in the biopharmaceutical industry for process optimization, scale-up and to reduce experimental effort. Parametric unstructured models based on biological mechanisms are highly promising, since they do not require large amounts of data. The critical part in the application is the certainty of the parameter estimates, since uncertainty of the parameter estimates propagates to model predictions and can increase the risk associated with those predictions.
View Article and Find Full Text PDFJ Biophotonics
January 2025
Department of Biomedical Engineering and Physics, Amsterdam UMC, Location University of Amsterdam, Amsterdam, The Netherlands.
In this study, we aim to validate the analytical Cramer-Rao lower bound (CRLB) equation for determining attenuation coefficients using a 1310 nm Optical Coherence Tomography (OCT) system. Our experimental results successfully confirm the validity of the equation, achieving unprecedented precision with a standard deviation below 0.01 mm for intralipid samples.
View Article and Find Full Text PDFArXiv
January 2025
Department of Mathematics, Penn State University, University Park, Pennsylvania, United States of America.
Practical identifiability is a critical concern in data-driven modeling of mathematical systems. In this paper, we propose a novel framework for practical identifiability analysis to evaluate parameter identifiability in mathematical models of biological systems. Starting with a rigorous mathematical definition of practical identifiability, we demonstrate its equivalence to the invertibility of the Fisher Information Matrix.
View Article and Find Full Text PDFJ Theor Biol
January 2025
Institut de Biologie, Ecole Normale Superieure, Paris, 75005, France; School of Biological Sciences, Georgia Institute of Technology, Atlanta, 30332, GA, USA; Department of Biology, University of Maryland, College Park, 20742, MD, USA. Electronic address:
Virus population dynamics are driven by counter-balancing forces of production and loss. Whereas viral production arises from complex interactions with susceptible hosts, the loss of infectious virus particles is often approximated as a first-order kinetic process. As such, experimental protocols to measure infectious virus loss are not typically designed to identify non-exponential decay processes.
View Article and Find Full Text PDFJ Appl Lab Med
December 2024
The Binding Site, part of Thermo Fisher Scientific, Rochester, MN, United States.
Background: Therapeutic monoclonal antibodies (t-mAbs) may interfere with electrophoresis-based methods used to monitor multiple myeloma (MM), which can create inaccurate results. Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry is an alternative to gels distinguishing between endogenous M-proteins and t-mAbs based on molecular mass.
Methods: Serum samples (n = 109) from 34 MM patients receiving Dara-KRd were collected 14 or 28 days postdaratumumab administration.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!