Overview of deep learning

Du, Xuedan; Cai, Yaqi; Wang, Shuo; Zhang, Leijie

doi:10.1109/yac.2016.7804882

Cited by 145 publications

(57 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…a large number of hidden layers and a greater number of neurons in each layer to learn deeper relations in data. The output from lower layers on which simple computations are performed is regarded as an input to the higher layers [2]. The increase in the network size demands an increase in processing speed and an increase in the size of data to take advantage of the deep structure.…”

Section: Org/wiki/a Rtifi Cial_neural_networkmentioning

confidence: 99%

Ensemble Learning on Deep Neural Networks for Image Caption Generation

Katpally

Bansal

2020

2020 IEEE 14th International Conference on Semantic Computing (ICSC)

View full text Add to dashboard Cite

Capturing the information in an image into a natural language sentence is considered a difficult problem to be solved by computers. Image captioning involves not just detecting objects from images but understanding the interactions between the objects to be translated into relevant captions. So, expertise in the fields of computer vision paired with natural language processing are supposed to be crucial for this purpose. The sequence to sequence modelling strategy of deep neural networks is the traditional approach to generate a sequential list of words which are combined to represent the image. But these models suffer from the problem of high variance by not being able to generalize well on the training data. The main focus of this thesis is to reduce the variance factor which will help in generating better captions. To achieve this, Ensemble Learning techniques have been explored, which have the reputation of solving the high variance problem that occurs in machine learning algorithms. Three different ensemble techniques namely, k-fold ensemble, bootstrap aggregation ensemble and boosting ensemble have been evaluated in this thesis. For each of these techniques, three output combination approaches have been analyzed. Extensive experiments have been conducted on the Flickr8k dataset which has a collection of 8000 images and 5 different captions for every image. The bleu score performance metric, which is considered to be the standard for evaluating natural language processing (NLP) problems, is used to evaluate the predictions. Based on this metric, the analysis shows that ensemble learning performs significantly better and generates more meaningful captions compared to any of the individual models used.

show abstract

Section: Org/wiki/a Rtifi Cial_neural_networkmentioning

confidence: 99%

Ensemble Learning on Deep Neural Networks for Image Caption Generation

Katpally

Bansal

2020

2020 IEEE 14th International Conference on Semantic Computing (ICSC)

View full text Add to dashboard Cite

show abstract

“…However, in more recent years, the use of a new technique known as deep learning has attracted the attention of researchers, since it has obtained remarkable results for various NLP tasks [13]. Deep Learning is a part of machine learning architecture including multiple layers of perceptron inspired by the human brain [14]. There are various deep learning models such as deep neural networks (DNN), convolution neural networks (CNN), deep Restricted Boltzmann Machine (RBM), etc.…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis of Online Product Reviews Using DLMNN and Future Prediction of Online Product Using IANFIS

Sasikala

Sheela

2020

Preprint

View full text Add to dashboard Cite

Sentiment analysis or opinion mining is one of the major tasks of NLP (Natural Language Processing). It captures the user’s opinion, feelings, and belief regarding the respective product especially to determine whether the user’s attitude is positive, negative, or neutral. This analysis greatly helps the companies to make necessary changes in their product which in return can overcome the flaws that the product is facing and targets better customer satisfaction. Existing techniques for the sentiment analysis of online product reviews obtained low accuracy and also took more time for training. To overcome such issues in this paper, a DLMNN is proposed for sentiment analysis of online product review and IANFIS is proposed for future prediction of online product. Here, the sentiment analysis and future predictions are done on the products taken from the food review dataset. First, from the dataset, the data values are partitioned into GB, CB, and CLB scenarios and then the review analysis for each scenario is performed separately using DLMNN and they give the result as positive, negative, and neutral reviews for the product. After the process of review classification based on these three scenarios, the future prediction of the products is done by performing weighting factor and classification using IANFIS. Experimental results are compared with some existing techniques and the results show that the proposed method outperforms other existing algorithms.

show abstract

“…As Deep Learning (DL) showed remarkable outcomes for an assortment of NLP tasks, it has captured the researchers' attention [22]. DL is a division of ML and it encompasses manifold layers of perceptron that is stimulated by means of the brain [23]. Numerous DL models are present, for instance deep neural networks (DNN), convolutions neural networks (CNN) [24], deep CNN [25], deep Restricted Boltzmanns Machine (RBM), etc.…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis of Online Product Reviews Using DLMNN and Future Prediction of Online Product Using IANFIS

Sasikala

Sheela

2020

Preprint

View full text Add to dashboard Cite

A major task that the NLP (Natural Language Processing) has to follow is Sentiments analysis (SA) or opinions mining (OM). For finding whether the user's attitude is positive, neutral or negative, it captures each user's opinion, belief, and feelings about the corresponding product. Through this, needed changes can well be done on the product for better customer contentment by the companies. Most of the existent techniques on SA aimed at these online products have extremely low accuracy and also encompassed more time amid training. By employing a Deep learning modified neural network (DLMNN), a technique is proposed aimed at SA of online products review; in addition, via Improved Adaptive Neuro-Fuzzy Inferences System (IANFIS), a technique is proposed aimed at future prediction of online products to trounce the above-stated issues. Firstly, the data values are separated into Contents-based (CB), Grades-based (GB), along with Collaborations based (CLB) setting as of the dataset. Then, each setting goes via review analysis (RA) by employing DLMNN, which renders the results as negative, positive, in addition to neutral reviews. IANFIS carry out a weighting factor and classification on the product for upcoming prediction. In the experimental assessment, the proposed work gave an enhanced performance compared to the existing methods.

show abstract

Overview of deep learning

Cited by 145 publications

References 19 publications

Ensemble Learning on Deep Neural Networks for Image Caption Generation

Ensemble Learning on Deep Neural Networks for Image Caption Generation

Sentiment Analysis of Online Product Reviews Using DLMNN and Future Prediction of Online Product Using IANFIS

Sentiment Analysis of Online Product Reviews Using DLMNN and Future Prediction of Online Product Using IANFIS

Contact Info

Product

Resources

About