Editorial introduction to the Neural Networks special issue on Deep Learning of Representations

Bengio, Yoshua; Lee, Honglak

doi:10.1016/j.neunet.2014.12.006

Cited by 44 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ML method teaches input relations -from examples to interpret new inputs. Therefore, their effectiveness is highly dependent on the choice of presentation data (or functions) that they perform [20]. Different models have been proposed to represent words as continuous vectors to evaluate the representation of subsequent words and generate distributed digital models (DSMs).…”

Section: Related Workmentioning

confidence: 99%

Automatic Relationship Construction in Domain Ontology Engineering using Semantic and Thematic Graph Generation Process and Convolution Neural Network

Guruvayur*¹,

Suchithra²

2019

IJRTE

View full text Add to dashboard Cite

In recent studies, Ontology construction plays an important role in translating raw text into useful knowledge. The proposed methodology supports efficient retrieval using multidimensional theory and implements integrated data training techniques before enter the trial process. The proposed approach has used the Semantic and Thematic Graph Generation Process to extract useful knowledge, and uses data mining techniques and web solutions to present knowledge as well as improve search speed and information retrieval accuracy. Established ontology can help clarify what it means for different ideas and relationships. Due to the rise of the ontology repository, the process of matching can take a long time. To avoid this, the method produces a hierarchical structure with in-depth interpretation of the data. A system is designed to remove domain dependencies using a dynamic labeling scheme using basic theorem, and the results show that it is possible to automatically and independently construct an independent domain

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Relationship Construction in Domain Ontology Engineering using Semantic and Thematic Graph Generation Process and Convolution Neural Network

Guruvayur*¹,

Suchithra²

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Deep learning is an evolving methodology, which represents more abstract concepts to discover better learning algorithms less dependent on feature engineering [3]. Deep learning implementations extract high-level features of complex data sets automatically through a special multi-layer neural network structure [10].…”

Section: Introductionmentioning

confidence: 99%

Regp: A New Pooling Algorithm for Deep Convolutional Neural Networks

Yıldırım¹,

Baloğlu²

2019

NNW

View full text Add to dashboard Cite

In this paper, we propose a new pooling method for deep convolutional neural networks. Previously introduced pooling methods either have very simple assumptions or they depend on stochastic events. Different from those methods, RegP pooling intensely investigates the input data. The main idea of this approach is finding the most distinguishing parts in regions of the input by investigating neighborhood regions to construct the pooled representation. RegP pooling improves the efficiency of the learning process, which is clearly visible in the experimental results. Further, the proposed pooling method outperformed other widely used hand-crafted pooling methods on several benchmark datasets.

show abstract

“…In [3], deep learning methods are used for simplifying a learning task from input examples. Based on scientific knowledge in the area of biology, cognitive humanoid autonomous methods with deep-learning-architecture have been proposed and applied over the years [4,11,19,28,30]. Deep learning replaces handcrafted feature extraction by learning unsupervised features as shown in [27].…”

Section: Introductionmentioning

confidence: 99%

Virtual Battery Parameter Identification Using Transfer Learning Based Stacked Autoencoder

Chakraborty

Nandanoori

Kundu

2018

2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Recent studies have shown that the aggregated dynamic flexibility of an ensemble of thermostatic loads can be modeled in the form of a virtual battery. The existing methods for computing the virtual battery parameters require the knowledge of the first-principle models and parameter values of the loads in the ensemble. In real-world applications, however, it is likely that the only available information are end-use measurements such as power consumption, room temperature, device on/off status, etc., while very little about the individual load models and parameters are known. We propose a transfer learning based deep network framework for calculating virtual battery state of a given ensemble of flexible thermostatic loads, from the available end-use measurements. This proposed framework extracts first order virtual battery model parameters for the given ensemble. We illustrate the effectiveness of this novel framework on different ensembles of ACs and WHs.

show abstract

Editorial introduction to the Neural Networks special issue on Deep Learning of Representations

Cited by 44 publications

References 23 publications

Automatic Relationship Construction in Domain Ontology Engineering using Semantic and Thematic Graph Generation Process and Convolution Neural Network

Automatic Relationship Construction in Domain Ontology Engineering using Semantic and Thematic Graph Generation Process and Convolution Neural Network

Regp: A New Pooling Algorithm for Deep Convolutional Neural Networks

Virtual Battery Parameter Identification Using Transfer Learning Based Stacked Autoencoder

Contact Info

Product

Resources

About