scholarly journals A Deep Learning Algorithm for the Max-Cut Problem Based on Pointer Network Structure with Supervised Learning and Reinforcement Learning Strategies

Mathematics ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 298 ◽  
Author(s):  
Shenshen Gu ◽  
Yue Yang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Reinforcement Learning ◽  
Combinatorial Optimization ◽  
Supervised Learning ◽  
Learning Strategies ◽  
Large Scale ◽  
Deep Neural Network ◽  
Max Cut Problem ◽  
Cut Problems

The Max-cut problem is a well-known combinatorial optimization problem, which has many real-world applications. However, the problem has been proven to be non-deterministic polynomial-hard (NP-hard), which means that exact solution algorithms are not suitable for large-scale situations, as it is too time-consuming to obtain a solution. Therefore, designing heuristic algorithms is a promising but challenging direction to effectively solve large-scale Max-cut problems. For this reason, we propose a unique method which combines a pointer network and two deep learning strategies (supervised learning and reinforcement learning) in this paper, in order to address this challenge. A pointer network is a sequence-to-sequence deep neural network, which can extract data features in a purely data-driven way to discover the hidden laws behind data. Combining the characteristics of the Max-cut problem, we designed the input and output mechanisms of the pointer network model, and we used supervised learning and reinforcement learning to train the model to evaluate the model performance. Through experiments, we illustrated that our model can be well applied to solve large-scale Max-cut problems. Our experimental results also revealed that the new method will further encourage broader exploration of deep neural network for large-scale combinatorial optimization problems.

scholarly journals Image Classification Using Transfer Learning and Deep Learning

2021 ◽  
Vol 10 (9) ◽  
pp. 25394-25398
Author(s):  
Chitra Desai
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Large Scale ◽  
Deep Neural Network ◽  
Visual Recognition ◽  
Classification Of Images

Deep learning models have demonstrated improved efficacy in image classification since the ImageNet Large Scale Visual Recognition Challenge started since 2010. Classification of images has further augmented in the field of computer vision with the dawn of transfer learning. To train a model on huge dataset demands huge computational resources and add a lot of cost to learning. Transfer learning allows to reduce on cost of learning and also help avoid reinventing the wheel. There are several pretrained models like VGG16, VGG19, ResNet50, Inceptionv3, EfficientNet etc which are widely used.   This paper demonstrates image classification using pretrained deep neural network model VGG16 which is trained on images from ImageNet dataset. After obtaining the convolutional base model, a new deep neural network model is built on top of it for image classification based on fully connected network. This classifier will use features extracted from the convolutional base model.

scholarly journals Share Market Prediction using Deep Neural Network

2019 ◽  
Vol 8 (3) ◽  
pp. 8619-8622
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Reinforcement Learning ◽  
Stock Market ◽  
Deep Neural Network ◽  
Learning Technology ◽  
Financial Investment ◽  
The Future ◽  
Future Prediction

People, due to their complexity and volatile actions, are constantly faced with challenges in understanding the situation in the market share and the forecast for the future. For any financial investment, the stock market is a very important aspect. It is necessary to study while understanding the price fluctuations of the stock market. In this paper, the stock market prediction model using the Recurrent Digital natural Network (RDNN) is described. The model is designed using two important machine learning concepts: the recurrent neural network (RNN), multilayer perceptron (MLP) and reinforcement learning (RL). Deep learning is used to automatically extract important functions of the stock market; reinforcement learning of these functions will be useful for future prediction of the stock market, the system uses historical stock market data to understand the dynamic market behavior when you make decisions in an unknown environment. In this paper, the understanding of the dynamic stock market and the deep learning technology for predicting the price of the future stock market are described.

scholarly journals Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China

2020 ◽  
Vol 10 (16) ◽  
pp. 5640
Author(s):  
Jingyu Yao ◽  
Shengwu Qin ◽  
Shuangshuang Qiao ◽  
Wenchao Che ◽  
Yang Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Supervised Learning ◽  
Landslide Susceptibility ◽  
Deep Neural Network ◽  
Spatial Information ◽  
Information Gain ◽  
Jilin Province ◽  
Landslide Susceptibility Mapping ◽  
Support Vector

Accurate and timely landslide susceptibility mapping (LSM) is essential to effectively reduce the risk of landslide. In recent years, deep learning has been successfully applied to landslide susceptibility assessment due to the strong ability of fitting. However, in actual applications, the number of labeled samples is usually not sufficient for the training component. In this paper, a deep neural network model based on semi-supervised learning (SSL-DNN) for landslide susceptibility is proposed, which makes full use of a large number of spatial information (unlabeled data) with limited labeled data in the region to train the mode. Taking Jiaohe County in Jilin Province, China as an example, the landslide inventory from 2000 to 2017 was collected and 12 metrological, geographical, and human explanatory factors were compiled. Meanwhile, supervised models such as deep neural network (DNN), support vector machine (SVM), and logistic regression (LR) were implemented for comparison. Then, the landslide susceptibility was plotted and a series of evaluation tools such as class accuracy, predictive rate curves (AUC), and information gain ratio (IGR) were calculated to compare the prediction of models and factors. Experimental results indicate that the proposed SSL-DNN model (AUC = 0.898) outperformed all the comparison models. Therefore, semi-supervised deep learning could be considered as a potential approach for LSM.

Comparison of Fundamental Learning Strategies for CBIR using Deep Learning Methods

2021 ◽  
Vol 14 ◽  
Author(s):  
Meenakshi Garg ◽  
Manisha Malhotra ◽  
Harpal Singh
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Learning Strategies ◽  
Deep Neural Network ◽  
Fuzzy Classification ◽  
Digital Archive ◽  
Large Database ◽  
Fuzzy Classifier ◽  
Neuro Fuzzy ◽  
Network Methods

Background: Photo retrieval based on contents is primarily used to retrieve photographs from a broad database. CBIR, also named "search by image," is an al-lowing technology that handles computerized images by its recognizable attributes. Methods: In other words, CBIR is a method for recovery of images that does not rely on annotations or keywords but on the characteristics of the images directly taken from the pictures. CBIR systems rely on the use of machine display methods in broad datasets for the image retrieval issue. The CBIR technology is the retrieval from a cluster of photos or archive of the most visually similar photographs to a particular query file.It is really useful for scanning photos, medical research etc. in other fields such as photography. It may be hard to visually find the images by inserting the metadata or keywords into a large database and cannot catch the keyword for identifying this image. CBIR allows the extraction of similar photographs from a digital archive with no labeling of photographs. The Deep Neural Network and Neuro-Fuzzy classification are contrasted in this article. They both have numerous findings and numerous tests to forecast the picture. Results: The analysis of the neuro-fuzzy and deep neural network methods we suggest reveals that the precision is increased. Conclusion: Accuracy values for DNN and Neuro-Fuzzy Classifier process are74.6% and 75.4%. For the validity of the proposed process, the visual and qualitative findings are provided.

scholarly journals A Study of incremental Learning model using deep neural network

2021 ◽  
Vol 10 (2) ◽  
pp. 658-663
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Computer Vision ◽  
Deep Learning ◽  
Supervised Learning ◽  
Incremental Learning ◽  
Deep Neural Network ◽  
Learning Model

Deep learning has arrived with a great number of advances in the research of machine learning and its models. Due to the advancements recently in the field of deep learning and its models especially in the fields like NLP and Computer Vision in supervised learning for which we have to pre-definably decide a dataset and train our model completely on it and make predictions but in case if we have any new samples of data on which we want our model to be predicted then we have to completely retrain the model, which is computationally costly therefore to avoid re-training the model, we add the new samples on the previously learnt features from the pre- trained model called Incremental Learning. In the paper we proposed the system to overcome the process of catastrophic forgetting we introduced the concept of building on pre-trained model.

scholarly journals An externally validated deep learning model for the accurate segmentation of the lumbar paravertebral muscles

2021 ◽  
Author(s):  
Frank Niemeyer ◽  
Annika Zanker ◽  
René Jonas ◽  
Youping Tao ◽  
Fabio Galbusera ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Large Scale ◽  
Deep Neural Network ◽  
External Validation ◽  
Erector Spinae ◽  
Published Data ◽  
Spinal Disorders ◽  
Paravertebral Muscles ◽  
Mri Scans

Purpose. Imaging studies about the relevance of muscles in spinal disorders, and sarcopenia in general, require the segmentation of the muscles in the images which is very labour-intensive if performed manually and poses a practical limit to the number of investigated subjects. This study aimed at developing a deep learning-based tool able to fully automatically perform an accurate segmentation of the lumbar muscles in axial MRI scans, and at validating the new tool on an external dataset. Methods. A set of 60 axial MRI images of the lumbar spine was retrospectively collected from a clinical database. Psoas major, quadratus lumborum, erector spinae, and multifidus were manually segmented in all available slices. The dataset was used to train and validate a deep neural network able to segment muscles automatically. Subsequently, the network was externally validated on images purposely acquired from 22 healthy volunteers. Results. The Jaccard index for the individual muscles calculated for the 22 subjects of the external validation set ranged between 0.862 and 0.935, demonstrating a generally excellent performance of the network. Cross-sectional area and fat fraction of the muscles were in agreement with published data. Conclusions. The externally validated deep neural network was able to perform the segmentation of the paravertebral muscles in axial MRI scans in an accurate and fully automated manner, and is therefore a suitable tool to perform large-scale studies in the field of spinal disorders and sarcopenia, overcoming the limitations of non-automated methods.

Chapter 14. Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning

2021 ◽  
Author(s):  
Hoifung Poon ◽  
Hai Wang ◽  
Hunter Lang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Supervised Learning ◽  
Latent Variables ◽  
Domain Knowledge ◽  
Deep Neural Network ◽  
Representation Learning ◽  
Probabilistic Logic ◽  
Initial Seed ◽  
Training Examples

Deep learning has proven effective for various application tasks, but its applicability is limited by the reliance on annotated examples. Self-supervised learning has emerged as a promising direction to alleviate the supervision bottleneck, but existing work focuses on leveraging co-occurrences in unlabeled data for task-agnostic representation learning, as exemplified by masked language model pretraining. In this chapter, we explore task-specific self-supervision, which leverages domain knowledge to automatically annotate noisy training examples for end applications, either by introducing labeling functions for annotating individual instances, or by imposing constraints over interdependent label decisions. We first present deep probabilistic logic (DPL), which offers a unifying framework for task-specific self-supervision by composing probabilistic logic with deep learning. DPL represents unknown labels as latent variables and incorporates diverse self-supervision using probabilistic logic to train a deep neural network end-to-end using variational EM. Next, we present self-supervised self-supervision (S4), which adds to DPL the capability to learn new self-supervision automatically. Starting from an initial seed self-supervision, S4 iteratively uses the deep neural network to propose new self supervision. These are either added directly (a form of structured self-training) or verified by a human expert (as in feature-based active learning). Experiments on real-world applications such as biomedical machine reading and various text classification tasks show that task-specific self-supervision can effectively leverage domain expertise and often match the accuracy of supervised methods with a tiny fraction of human effort.

scholarly journals A State-of-the-Art Survey on Deep Learning Theory and Architectures

Electronics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 292 ◽  
Author(s):  
Md Zahangir Alom ◽  
Tarek M. Taha ◽  
Chris Yakopcic ◽  
Stefan Westberg ◽  
Paheding Sidike ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Reinforcement Learning ◽  
Language Processing ◽  
Large Scale ◽  
Medical Information ◽  
State Of The Art ◽  
Generative Models ◽  
Learning Approaches

In recent years, deep learning has garnered tremendous success in a variety of application domains. This new field of machine learning has been growing rapidly and has been applied to most traditional application domains, as well as some new areas that present more opportunities. Different methods have been proposed based on different categories of learning, including supervised, semi-supervised, and un-supervised learning. Experimental results show state-of-the-art performance using deep learning when compared to traditional machine learning approaches in the fields of image processing, computer vision, speech recognition, machine translation, art, medical imaging, medical information processing, robotics and control, bioinformatics, natural language processing, cybersecurity, and many others. This survey presents a brief survey on the advances that have occurred in the area of Deep Learning (DL), starting with the Deep Neural Network (DNN). The survey goes on to cover Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), including Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), Auto-Encoder (AE), Deep Belief Network (DBN), Generative Adversarial Network (GAN), and Deep Reinforcement Learning (DRL). Additionally, we have discussed recent developments, such as advanced variant DL techniques based on these DL approaches. This work considers most of the papers published after 2012 from when the history of deep learning began. Furthermore, DL approaches that have been explored and evaluated in different application domains are also included in this survey. We also included recently developed frameworks, SDKs, and benchmark datasets that are used for implementing and evaluating deep learning approaches. There are some surveys that have been published on DL using neural networks and a survey on Reinforcement Learning (RL). However, those papers have not discussed individual advanced techniques for training large-scale deep learning models and the recently developed method of generative models.

A Deep Neural Network Model for Cross-Domain Sentiment Analysis

2021 ◽  
Vol 12 (2) ◽  
pp. 1-16
Author(s):  
Suman Kumari ◽  
Basant Agarwal ◽  
Mamta Mittal
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Supervised Learning ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Analysis Model ◽  
Cross Domain ◽  
Unstructured Text

Sentiment analysis is used to detect the opinion/sentiment expressed from the unstructured text. Most of the existing state-of-the-art methods are based on supervised learning, and therefore, a labelled dataset is required to build the model, and it is very difficult task to obtain a labelled dataset for every domain. Cross-domain sentiment analysis is to develop a model which is trained on labelled dataset of one domain, and the performance is evaluated on another domain. The performance of such cross-domain sentiment analysis is still very limited due to presence of many domain-related terms, and the sentiment analysis is a domain-dependent problem in which words changes their polarity depending upon the domain. In addition, cross-domain sentiment analysis model suffers with the problem of large number of out-of-the-vocabulary (unseen words) words. In this paper, the authors propose a deep learning-based approach for cross-domain sentiment analysis. Experimental results show that the proposed approach improves the performance on the benchmark dataset.

Sign in / Sign up

Export Citation Format

Share Document