Explainable Deep Learning Reproduces a ‘Professional Eye’ on the Diagnosis of Internal Disorders in Persimmon Fruit

2020 ◽  
Vol 61 (11) ◽  
pp. 1967-1973
Author(s):  
Takashi Akagi ◽  
Masanori Onishi ◽  
Kanae Masuda ◽  
Ryohei Kuroki ◽  
Kohei Baba ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Binary Classification ◽  
Network Models ◽  
Plant Biology ◽  
Neural Network Models ◽  
Persimmon Fruit

Abstract Recent rapid progress in deep neural network techniques has allowed recognition and classification of various objects, often exceeding the performance of the human eye. In plant biology and crop sciences, some deep neural network frameworks have been applied mainly for effective and rapid phenotyping. In this study, beyond simple optimizations of phenotyping, we propose an application of deep neural networks to make an image-based internal disorder diagnosis that is hard even for experts, and to visualize the reasons behind each diagnosis to provide biological interpretations. Here, we exemplified classification of calyx-end cracking in persimmon fruit by using five convolutional neural network models with various layer structures and examined potential analytical options involved in the diagnostic qualities. With 3,173 visible RGB images from the fruit apex side, the neural networks successfully made the binary classification of each degree of disorder, with up to 90% accuracy. Furthermore, feature visualizations, such as Grad-CAM and LRP, visualize the regions of the image that contribute to the diagnosis. They suggest that specific patterns of color unevenness, such as in the fruit peripheral area, can be indexes of calyx-end cracking. These results not only provided novel insights into indexes of fruit internal disorders but also proposed the potential applicability of deep neural networks in plant biology.

Building on prior knowledge without building it in

2017 ◽  
Vol 40 ◽  
Author(s):  
Steven S. Hansen ◽  
Andrew K. Lampinen ◽  
Gaurav Suri ◽  
James L. McClelland
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Prior Knowledge ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Network Models ◽  
Causal Models ◽  
Neural Network Models ◽  
Start Up ◽  
The Many

AbstractLake et al. propose that people rely on “start-up software,” “causal models,” and “intuitive theories” built using compositional representations to learn new tasks more efficiently than some deep neural network models. We highlight the many drawbacks of a commitment to compositional representations and describe our continuing effort to explore how the ability to build on prior knowledge and to learn new tasks efficiently could arise through learning in deep neural networks.

scholarly journals Determining the Age of the Author of the Text Based on Deep Neural Network Models

Information ◽  
2020 ◽  
Vol 11 (12) ◽  
pp. 589 ◽  
Author(s):  
Aleksandr Sergeevich Romanov ◽  
Anna Vladimirovna Kurtukova ◽  
Artem Alexandrovich Sobolev ◽  
Alexander Alexandrovich Shelupanov ◽  
Anastasia Mikhailovna Fedotova
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Network Models ◽  
Russian Language ◽  
Neural Network Models ◽  
Inaccurate Data ◽  
Language Text

This paper is devoted to solving the problem of determining the age of the author of the text based on models of deep neural networks. The article presents an analysis of methods for determining the age of the author of a text and approaches to determining the age of a user by a photo. This could be a solution to the problem of inaccurate data for training by filtering out incorrect user-specified age data. A detailed description of the author’s technique based on deep neural network models and the interpretation of the results is also presented. The study found that the proposed technique achieved 82% accuracy in determining the age of the author from Russian-language text, which makes it competitive in comparison with approaches for other languages.

Inclusion of Multiple Cycling of the Potential into Deep Neural Network Classification of Voltammetric Reaction Mechanisms

2021 ◽  
Author(s):  
Luke Gundry ◽  
Gareth Kennedy ◽  
Alan Bond ◽  
Jie Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reaction Mechanisms ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Neural Network Classification ◽  
Initial Cycle

The use of Deep Neural Networks (DNNs) for the classification of electrochemical mechanisms based on training with simulations of the initial cycle of potential have been reported. In this paper,...

scholarly journals Feature-Based Interpretation of the Deep Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2687
Author(s):  
Eun-Hun Lee ◽  
Hyeoncheol Kim
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Network ◽  
Lower Layer ◽  
Network Models ◽  
Neural Network Models ◽  
Network Pruning ◽  
The Neural Network ◽  
Single Instance ◽  
High Level

The significant advantage of deep neural networks is that the upper layer can capture the high-level features of data based on the information acquired from the lower layer by stacking layers deeply. Since it is challenging to interpret what knowledge the neural network has learned, various studies for explaining neural networks have emerged to overcome this problem. However, these studies generate the local explanation of a single instance rather than providing a generalized global interpretation of the neural network model itself. To overcome such drawbacks of the previous approaches, we propose the global interpretation method for the deep neural network through features of the model. We first analyzed the relationship between the input and hidden layers to represent the high-level features of the model, then interpreted the decision-making process of neural networks through high-level features. In addition, we applied network pruning techniques to make concise explanations and analyzed the effect of layer complexity on interpretability. We present experiments on the proposed approach using three different datasets and show that our approach could generate global explanations on deep neural network models with high accuracy and fidelity.

scholarly journals Classification of heterogeneous precipitation fields for the assessment and possible improvement of lumped neural network models for streamflow forecasts

2006 ◽  
Vol 3 (1) ◽  
pp. 201-227 ◽  
Author(s):  
N. Lauzon ◽  
F. Anctil ◽  
C. W. Baxter
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Multilayer Perceptron ◽  
Network Models ◽  
Rainfall Runoff ◽  
Neural Network Models ◽  
Kohonen Neural Network ◽  
Streamflow Forecasts ◽  
Rainfall Runoff Model

Abstract. This work addresses the issue of better considering the heterogeneity of precipitation fields within lumped rainfall-runoff models where only areal mean precipitation is usually used as an input. A method using a Kohonen neural network is proposed for the classification of precipitation fields. The evaluation and improvement of the performance of a lumped rainfall-runoff model for one-day ahead predictions is then established based on this classification. Multilayer perceptron neural networks are employed as lumped rainfall-runoff models. The Bas-en-Basset watershed in France, which is equipped with 23 rain gauges with data for a 21-year period, is employed as the application case. The results demonstrate the relevance of the proposed classification method, which produces groups of precipitation fields that are in agreement with the global climatological features affecting the region, as well as with the topographic constraints of the watershed (i.e., orography). The strengths and weaknesses of the rainfall-runoff models are highlighted by the analysis of their performance vis-à-vis the classification of precipitation fields. The results also show the capability of multilayer perceptron neural networks to account for the heterogeneity of precipitation, even when built as lumped rainfall-runoff models.

scholarly journals Deep neural network models reveal interplay of peripheral coding and stimulus statistics in pitch perception

2020 ◽  
Author(s):  
Mark R. Saddler ◽  
Ray Gonzalez ◽  
Josh H. McDermott
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Neural Coding ◽  
Deep Neural Network ◽  
Network Models ◽  
Pitch Perception ◽  
Natural Environments ◽  
Sensory Receptors ◽  
Natural Sounds ◽  
Neural Network Models

ABSTRACTComputations on receptor responses enable behavior in the environment. Behavior is plausibly shaped by both the sensory receptors and the environments for which organisms are optimized, but their roles are often opaque. One classic example is pitch perception, whose properties are commonly linked to peripheral neural coding limits rather than environmental acoustic constraints. We trained artificial neural networks to estimate fundamental frequency from simulated cochlear representations of natural sounds. The best-performing networks replicated many characteristics of human pitch judgments. To probe how our ears and environment shape these characteristics, we optimized networks given altered cochleae or sound statistics. Human-like behavior emerged only when cochleae had high temporal fidelity and when models were optimized for natural sounds. The results suggest pitch perception is critically shaped by the constraints of natural environments in addition to those of the cochlea, illustrating the use of contemporary neural networks to reveal underpinnings of behavior.

scholarly journals APPLICATION OF NEURAL NETWORKS TO DETERMINE THE COORDINATES OF THE SEAT OF FIRE BY MULTIPOINT ELECTRO-OPTICAL SYSTEM

2021 ◽  
pp. 248-251
Author(s):  
Д.Ф. Пирова ◽  
Б.Э. Забержинский ◽  
А.Г. Золин
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Performance ◽  
Network Models ◽  
X Rays ◽  
Neural Network Models ◽  
X Ray ◽  
Python Programming Language ◽  
Python Programming

Статья посвящена исследованию методов проектирования интеллектуальных информационных систем и применение моделей искусственных нейронных сетей для диагностического прогнозирования развития пневмонии посредством анализа рентгеновских снимков. В этой работе основное внимание уделяется классификации пневмонии и туберкулеза - двух основных заболеваний грудной клетки - на основе рентгеновских снимков грудной клетки. Данное исследование проводилось при помощи открытой нейросетевой библиотеки Keras и языка программирования Python. Система дает пользователю заключение о том, болен он или нет, тем самым помогая врачам и медицинскому персоналу принять быстрое и информированное решение о наличии заболевания. Разработанная модель, может определить, является ли рентгеновский снимок нормальным или имеет отклонения, которые могут быть пневмонией с точностью 94,87%. Полученные результаты указывают на высокую эффективность применения нейронных сетей при диагностировании пневмонии по рентгеновским снимкам. This paper is devoted to the study of methods of designing intellectual information systems and neural network models application on diagnostic prediction of pneumonia development by X-ray images analysis. This article focuses on the classification of pneumonia and tuberculosis - the two main chest diseases - based on chest x-rays. This study was carried out using the Keras open neural network library and the Python programming language. System returns user a conclusion whether the patient is ill or not helping medical staff to make a quick and informed decision about the presence of the disease. The developed model can determine is the X-ray image normal or has anomalies that can be pneumonia with accuracy up to 94.87%. The results obtained indicate the high performance of the applying neural networks in the diagnosis of pneumonia by X-ray images.

scholarly journals A Novel Low-Bit Quantization Strategy for Compressing Deep Neural Networks

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Xin Long ◽  
XiangRong Zeng ◽  
Zongcheng Ben ◽  
Dianle Zhou ◽  
Maojun Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Network Models ◽  
Memory Consumption ◽  
Neural Network Models ◽  
The Neural Network ◽  
The Neural Networks ◽  
Novel Strategy

The increase in sophistication of neural network models in recent years has exponentially expanded memory consumption and computational cost, thereby hindering their applications on ASIC, FPGA, and other mobile devices. Therefore, compressing and accelerating the neural networks are necessary. In this study, we introduce a novel strategy to train low-bit networks with weights and activations quantized by several bits and address two corresponding fundamental issues. One is to approximate activations through low-bit discretization for decreasing network computational cost and dot-product memory. The other is to specify weight quantization and update mechanism for discrete weights to avoid gradient mismatch. With quantized low-bit weights and activations, the costly full-precision operation will be replaced by shift operation. We evaluate the proposed method on common datasets, and results show that this method can dramatically compress the neural network with slight accuracy loss.

scholarly journals Surrogate Object Detection Explainer (SODEx) with YOLOv4 and LIME

2021 ◽  
Vol 3 (3) ◽  
pp. 662-671
Author(s):  
Jonas Herskind Sejr ◽  
Peter Schneider-Kamp ◽  
Naeem Ayoub
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Deep Neural Networks ◽  
Empirical Evaluation ◽  
Network Models ◽  
Detection Algorithm ◽  
Neural Network Models ◽  
The Neural Network

Due to impressive performance, deep neural networks for object detection in images have become a prevalent choice. Given the complexity of the neural network models used, users of these algorithms are typically given no hint as to how the objects were found. It remains, for example, unclear whether an object is detected based on what it looks like or based on the context in which it is located. We have developed an algorithm, Surrogate Object Detection Explainer (SODEx), that can explain any object detection algorithm using any classification explainer. We evaluate SODEx qualitatively and quantitatively by detecting objects in the COCO dataset with YOLOv4 and explaining these detections with LIME. This empirical evaluation does not only demonstrate the value of explainable object detection, it also provides valuable insights into how YOLOv4 detects objects.

scholarly journals Detecting failure modes in image reconstructions with interval neural network uncertainty

2021 ◽  
Author(s):  
Luis Oala ◽  
Cosmas Heiß ◽  
Jan Macdonald ◽  
Maximilian März ◽  
Gitta Kutyniok ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Reconstruction ◽  
Deep Neural Networks ◽  
Failure Modes ◽  
Network Models ◽  
Quantitative Detection ◽  
Neural Network Models ◽  
Post Hoc ◽  
Interval Neural Network

Abstract Purpose The quantitative detection of failure modes is important for making deep neural networks reliable and usable at scale. We consider three examples for common failure modes in image reconstruction and demonstrate the potential of uncertainty quantification as a fine-grained alarm system. Methods We propose a deterministic, modular and lightweight approach called Interval Neural Network (INN) that produces fast and easy to interpret uncertainty scores for deep neural networks. Importantly, INNs can be constructed post hoc for already trained prediction networks. We compare it against state-of-the-art baseline methods (MCDrop, ProbOut). Results We demonstrate on controlled, synthetic inverse problems the capacity of INNs to capture uncertainty due to noise as well as directional error information. On a real-world inverse problem with human CT scans, we can show that INNs produce uncertainty scores which improve the detection of all considered failure modes compared to the baseline methods. Conclusion Interval Neural Networks offer a promising tool to expose weaknesses of deep image reconstruction models and ultimately make them more reliable. The fact that they can be applied post hoc to equip already trained deep neural network models with uncertainty scores makes them particularly interesting for deployment.

Sign in / Sign up

Export Citation Format

Share Document