scholarly journals On the modeling of error functions as high dimensional landscapes for weight initialization in learning networks

2016 ◽  
Author(s):  
Julius ◽  
Gopinath Mahale ◽  
T. Sumana ◽  
C. S. Adityakrishna
Keyword(s):  
High Dimensional ◽  
Learning Networks ◽  
Error Functions ◽  
Weight Initialization

scholarly journals Recurrent dynamics in the cerebral cortex: Integration of sensory evidence with stored knowledge

2021 ◽  
Vol 118 (33) ◽  
pp. e2101043118
Author(s):  
Wolf Singer
Keyword(s):  
Cerebral Cortex ◽  
Sensory Processing ◽  
Complex Dynamics ◽  
Predictive Coding ◽  
High Dimensional ◽  
Learning Networks ◽  
Feed Forward ◽  
Weight Distributions ◽  
The World ◽  
Sensory Evidence

Current concepts of sensory processing in the cerebral cortex emphasize serial extraction and recombination of features in hierarchically structured feed-forward networks in order to capture the relations among the components of perceptual objects. These concepts are implemented in convolutional deep learning networks and have been validated by the astounding similarities between the functional properties of artificial systems and their natural counterparts. However, cortical architectures also display an abundance of recurrent coupling within and between the layers of the processing hierarchy. This massive recurrence gives rise to highly complex dynamics whose putative function is poorly understood. Here a concept is proposed that assigns specific functions to the dynamics of cortical networks and combines, in a unifying approach, the respective advantages of recurrent and feed-forward processing. It is proposed that the priors about regularities of the world are stored in the weight distributions of feed-forward and recurrent connections and that the high-dimensional, dynamic space provided by recurrent interactions is exploited for computations. These comprise the ultrafast matching of sensory evidence with the priors covertly represented in the correlation structure of spontaneous activity and the context-dependent grouping of feature constellations characterizing natural objects. The concept posits that information is encoded not only in the discharge frequency of neurons but also in the precise timing relations among the discharges. Results of experiments designed to test the predictions derived from this concept support the hypothesis that cerebral cortex exploits the high-dimensional recurrent dynamics for computations serving predictive coding.

scholarly journals Medical Augmentation (Med-Aug) for Optimal Data Augmentation in Medical Deep Learning Networks

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7018
Author(s):  
Justin Lo ◽  
Jillian Cardinell ◽  
Alejo Costanzo ◽  
Dafna Sussman
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Data Augmentation ◽  
Search Algorithm ◽  
High Dimensional ◽  
Learning Networks ◽  
Imaging Data ◽  
Covariance Matrix Adaptation ◽  
Using Data ◽  
Adaptation Evolution

Deep learning (DL) algorithms have become an increasingly popular choice for image classification and segmentation tasks; however, their range of applications can be limited. Their limitation stems from them requiring ample data to achieve high performance and adequate generalizability. In the case of clinical imaging data, images are not always available in large quantities. This issue can be alleviated by using data augmentation (DA) techniques. The choice of DA is important because poor selection can possibly hinder the performance of a DL algorithm. We propose a DA policy search algorithm that offers an extended set of transformations that accommodate the variations in biomedical imaging datasets. The algorithm makes use of the efficient and high-dimensional optimizer Bi-Population Covariance Matrix Adaptation Evolution Strategy (BIPOP-CMA-ES) and returns an optimal DA policy based on any input imaging dataset and a DL algorithm. Our proposed algorithm, Medical Augmentation (Med-Aug), can be implemented by other researchers in related medical DL applications to improve their model’s performance. Furthermore, we present our found optimal DA policies for a variety of medical datasets and popular segmentation networks for other researchers to use in related tasks.

Mathematical simulation of error functions of decision-making at tolerance control of measuring techniques availability

Metrologiya ◽  
2020 ◽  
pp. 3-15
Author(s):  
Rustam Z. Khayrullin ◽  
Alexey S. Kornev ◽  
Andrew A. Kostoglotov ◽  
Sergey V. Lazarenko
Keyword(s):  
Measurement Error ◽  
Geometric Interpretation ◽  
Measuring Instruments ◽  
Measured Quantity ◽  
Metrological Examination ◽  
Technical Documentation ◽  
Error Functions ◽  
Measuring Techniques ◽  
Tolerance Control ◽  
Laws Of Distribution

Analytical and computer models of false failure and undetected failure (error functions) were developed with tolerance control of the parameters of the components of the measuring technique. A geometric interpretation of the error functions as two-dimensional surfaces is given, which depend on the tolerance on the controlled parameter and the measurement error. The developed models are applicable both to theoretical laws of distribution, and to arbitrary laws of distribution of the measured quantity and measurement error. The results can be used in the development of metrological support of measuring equipment, the verification of measuring instruments, the metrological examination of technical documentation and the certification of measurement methods.

Sign in / Sign up

Export Citation Format

Share Document