Multilingual Sentiment Recommendation System based on Multilayer Convolutional Neural Networks (MCNN) and Collaborative Filtering based Multistage Deep Neural Network Models (CFMDNN)

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.

Download Full-text

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

Plant and Cell Physiology ◽

10.1093/pcp/pcaa111 ◽

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.

Download Full-text

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

10.1101/2020.11.19.389999 ◽

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.

Download Full-text

Novel convolutional neural networks for efficient classification of rotated and scaled images

Neural Computing and Applications ◽

10.1007/s00521-021-06645-9 ◽

2021 ◽

Author(s):

Paweł Tarasiuk ◽

Piotr S. Szczepaniak

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Networks ◽

Network Architecture ◽

Data Augmentation ◽

Network Models ◽

Input Image ◽

Feature Maps ◽

Neural Network Models ◽

Geometric Transformations

AbstractThis paper presents a novel method for improving the invariance of convolutional neural networks (CNNs) to selected geometric transformations in order to obtain more efficient image classifiers. A common strategy employed to achieve this aim is to train the network using data augmentation. Such a method alone, however, increases the complexity of the neural network model, as any change in the rotation or size of the input image results in the activation of different CNN feature maps. This problem can be resolved by the proposed novel convolutional neural network models with geometric transformations embedded into the network architecture. The evaluation of the proposed CNN model is performed on the image classification task with the use of diverse representative data sets. The CNN models with embedded geometric transformations are compared to those without the transformations, using different data augmentation setups. As the compared approaches use the same amount of memory to store the parameters, the improved classification score means that the proposed architecture is more optimal.

Download Full-text

Building on prior knowledge without building it in

Behavioral and Brain Sciences ◽

10.1017/s0140525x17000176 ◽

2017 ◽

Vol 40 ◽

Cited By ~ 2

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.

Download Full-text

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

Information ◽

10.3390/info11120589 ◽

2020 ◽

Vol 11 (12) ◽

pp. 589 ◽

Cited By ~ 1

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.

Download Full-text