Poziom rozwoju społeczno-gospodarczego w powiatach województwa wielkopolskiego

Józefowicz, Karolina; Smolińska, Kinga

doi:10.22630/tirr.2019.11.4

Cited by 11 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In an inversion of the “unrolling” of the RNN into multiple time‐stages, here, we could use the feedback from CA1 to DG via EC as the recurrence step, to “roll” up the multiple stages of input into sequentially arriving inputs. Several studies have pointed out that the exact details of the internal stages in an RNN are not crucial for the capabilities of deep learning and sequence computation (Greff, Srivastava, Koutník, Steunebrink, & Schmidhuber,, 2017; Jozefowicz, Zaremba, & Sutskever, ). Therefore, the functional analogy with the hippocampus does not necessarily need one‐to‐one mappings of circuitry.…”

Section: Parallels Between Deep Learning Network and The Hippocampusmentioning

confidence: 99%

Dendrites, deep learning, and sequences in the hippocampus

Bhalla

2017

Hippocampus

View full text Add to dashboard Cite

The hippocampus places us both in time and space. It does so over remarkably large spans: milliseconds to years, and centimeters to kilometers. This works for sensory representations, for memory, and for behavioral context. How does it fit in such wide ranges of time and space scales, and keep order among the many dimensions of stimulus context? A key organizing principle for a wide sweep of scales and stimulus dimensions is that of order in time, or sequences. Sequences of neuronal activity are ubiquitous in sensory processing, in motor control, in planning actions, and in memory. Against this strong evidence for the phenomenon, there are currently more models than definite experiments about how the brain generates ordered activity. The flip side of sequence generation is discrimination. Discrimination of sequences has been extensively studied at the behavioral, systems, and modeling level, but again physiological mechanisms are fewer. It is against this backdrop that I discuss two recent developments in neural sequence computation, that at face value share little beyond the label "neural." These are dendritic sequence discrimination, and deep learning. One derives from channel physiology and molecular signaling, the other from applied neural network theory - apparently extreme ends of the spectrum of neural circuit detail. I suggest that each of these topics has deep lessons about the possible mechanisms, scales, and capabilities of hippocampal sequence computation.

show abstract

Section: Parallels Between Deep Learning Network and The Hippocampusmentioning

confidence: 99%

Dendrites, deep learning, and sequences in the hippocampus

Bhalla

2017

Hippocampus

View full text Add to dashboard Cite

show abstract

“…This layer was used to uniform the different image sequence lengths. At the end of the model, we added two FC layers (the first one has 1024 nodes, and the second one has two nodes for benign/malignant) and the softmax activation to achieve diagnosis at the patient level.Model two [gated recurrent unit (GRU) [28] model]: In the GRU model, the feature vectors (1024 × 1 × N) of each patient were extracted in the same way as described above; however, the feature vectors should be concatenated into a 2D array(1024 × N) as the input image sequence. After two GRU layers of this model, softmax activation function was used to achieve the patient-level classification result.…”

Section: Methodsmentioning

confidence: 99%

“…Model two [gated recurrent unit (GRU) [28] model]: In the GRU model, the feature vectors (1024 × 1 × N) of each patient were extracted in the same way as described above; however, the feature vectors should be concatenated into a 2D array(1024 × N) as the input image sequence. After two GRU layers of this model, softmax activation function was used to achieve the patient-level classification result.…”

Section: Methodsmentioning

confidence: 99%

A Deep Learning-Based Radiomics Model for Differentiating Benign and Malignant Renal Tumors

Zhou

Zhang

Chen

et al. 2019

Translational Oncology

129

View full text Add to dashboard Cite

OBJECTIVES: To investigate the effect of transfer learning on computed tomography (CT) images for the benign and malignant classification on renal tumors and to attempt to improve the classification accuracy by building patient-level models. METHODS: One hundred ninety-two cases of renal tumors were collected and identified by pathologic diagnosis within 15 days after enhanced CT examination (66% male, 70% malignant renal tumors, average age of 62.27 ± 12.26 years). The InceptionV3 model pretrained by the ImageNet dataset was cross-trained to perform this classification. Five image-level models were established for each of the Slice, region of interest (ROI), and rectangular box region (RBR) datasets. Then, two patient-level models were built based on the optimal image-level models. The network's performance was evaluated through analysis of the receiver operating characteristic (ROC) and five-fold cross-validation. RESULTS: In the image-level models, the test results of model trained on the Slice dataset [accuracy (ACC) = 0.69 and Matthews correlation coefficient (MCC) = 0.45] were the worst. The corresponding results on the ROI dataset (ACC = 0.97 and MCC = 0.93) were slightly better than those on the RBR dataset (ACC = 0.93 and MCC = 0.85) when freezing the weights before the mixed6 layer. Compared with the image-level models, both patient-level models could discriminate better (ACC increased by 2%-5%) on the RBR and Slice datasets. CONCLUSIONS: Deep learning can be used to classify benign and malignant renal tumors from CT images. Our patient-level models could benefit from 3D data to improve the accuracy.

show abstract

“…Considering the above limitations, based on the analysis of the literature, a number of demographic, social, and environmental indicators were selected for the research conducted in this article [86][87][88][89][90][91][92][93][94][95]. The following in Table 1 lists the selected factors (variables), broken down by thematic sections.…”

Section: Data Source and Processingmentioning

confidence: 99%

Influence of the Demographic, Social, and Environmental Factors on the COVID-19 Pandemic—Analysis of the Local Variations Using Geographically Weighted Regression

Rząsa

Ciski

2022

IJERPH

View full text Add to dashboard Cite

As the COVID-19 pandemic continues, an increasing number of different research studies focusing on various aspects of the pandemic are emerging. Most of the studies focus on the medical aspects of the pandemic, as well as on the impact of COVID-19 on various areas of life; less emphasis is put on analyzing the influence of socio-environmental factors on the spread of the pandemic. In this paper, using the geographically weighted regression method, the extent to which demographic, social, and environmental factors explain the number of cases of SARS-CoV-2 is explored. The research was performed for the case-study area of Poland, considering the administrative division of the country into counties. The results showed that the demographic factors best explained the number of cases of SARS-CoV-2; the social factors explained it to a medium degree; and the environmental factors explained it to the lowest degree. Urban population and the associated higher amount and intensity of human contact are the most influential factors in the development of the COVID-19 pandemic. The analysis of the factors related to the areas burdened by social problems resulting primarily from the economic exclusion revealed that poverty-burdened areas are highly vulnerable to the development of the COVID-19 pandemic. Using maps of the local R2 it was possible to visualize how the relationships between the explanatory variables (for this research—demographic, social, and environmental factors) and the dependent variable (number of cases of SARS-CoV-2) vary across the study area. Through the GWR method, counties were identified as particularly vulnerable to the pandemic because of the problem of economic exclusion. Considering that the COVID-19 pandemic is still ongoing, the results obtained may be useful for local authorities in developing strategies to counter the pandemic.

show abstract

Poziom rozwoju społeczno-gospodarczego w powiatach województwa wielkopolskiego

Cited by 11 publications

References 6 publications

Dendrites, deep learning, and sequences in the hippocampus

Dendrites, deep learning, and sequences in the hippocampus

A Deep Learning-Based Radiomics Model for Differentiating Benign and Malignant Renal Tumors

Influence of the Demographic, Social, and Environmental Factors on the COVID-19 Pandemic—Analysis of the Local Variations Using Geographically Weighted Regression

Contact Info

Product

Resources

About