Adversarial Optimization-Based Knowledge Transfer of Layer-Wise Dense Flow for Image Classification

Yeo, Doyeob; Kim, Min-Suk; Bae, Ji‐Hoon

doi:10.3390/app11083720

Cited by 3 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…satisfying (5). Then, we can just put the input/output datasets into the regression model or neural network to get the best estimate of the parameters under the given assumptions.…”

Section: B Problem Definition and Preliminary Resultsmentioning

confidence: 99%

A New Approach to Neural Network Design for Fast Convergence via Feed-forward Loop

2022

IJMLC

View full text Add to dashboard Cite

A feed-forward loop has been widely used in control systems to boost the performance without hurting the overall stability of the system. We propose a new neural network, FfcNet by adopting the idea from the control theory. The proposed network adds a pre-designed feed-forward loop in parallel with the existing regular blocks, which is similar to the identity mapping in ResNet network. The feed-forward loop helps the overall network to converge faster while keeping overall system stability and accuracy. It is also shown that the feed-forward loop is equivalent to setting a proper initial condition of the parameters in the network. A special dataset of highly distorted 7-segment LED images is prepared to evaluate the performance of the pattern recognition algorithm. We demonstrated the performance of the proposed design through simulations and found the new design improved the convergence rate by 52% from the original ResNet network while keeping the same test accuracy.

show abstract

“…satisfying (5). Then, we can just put the input/output datasets into the regression model or neural network to get the best estimate of the parameters under the given assumptions.…”

Section: B Problem Definition and Preliminary Resultsmentioning

confidence: 99%

A New Approach to Neural Network Design for Fast Convergence via Feed-forward Loop

2022

IJMLC

View full text Add to dashboard Cite

show abstract

“…The attitude of top managers in universities is very important. The so-called attitude influences how other people feel about the behavior and meaning of it [49][50][51][52][53]. Thus, top managers should strengthen their management and decision-making efficiency to improve the scientific decision-making standard.…”

Section: Organizational Culture Aspectmentioning

confidence: 99%

“…(2) Internal Incentive System Kopytova [74] believed that incentives are an intrinsic or extrinsic force that gives people enthusiasm to take actions to achieve a specific goal. However, Lee et al [50] believed that incentives make employees in an organization work harder, inspire their inner power and willingness, and attempt to satisfy employees' needs. Fang et al [75] mentioned that technology developers are producers of intellectual property rights.…”

Section: Organizational Structure and System Aspectmentioning

confidence: 99%

“…The proposed approach employs LDA and LSTM as basic strategies for validity appraisal. Yeo et al [50] proposed a layer-wise dense flow (LDF)-based knowledge transfer technique. Yeo et al [50] attempted to apply a deeplearning innovation for information exchange that is vital to progress and optimizing effective information refining.…”

Section: Essence Of Technology Aspectmentioning

confidence: 99%

“…Yeo et al [50] proposed a layer-wise dense flow (LDF)-based knowledge transfer technique. Yeo et al [50] attempted to apply a deeplearning innovation for information exchange that is vital to progress and optimizing effective information refining. Yeo [50] point to create a modern antagonistic optimizationbased information exchange strategy including a layer-wise thick stream that is refined from a pre-trained, profound neural organization (DNN).…”

Section: Essence Of Technology Aspectmentioning

confidence: 99%

See 2 more Smart Citations

Evaluating the Intertwined Relationships of the Drivers for University Technology Transfer

Sun

2021

Applied Sciences

View full text Add to dashboard Cite

Universities are the best places to gather knowledge and innovation, but the basis of technological development lies in talented R&D personnel who provide services to enterprise R&D activities, research institutions, and universities. Universities also gather many elites who cultivate talent for the country. However, universities do not have adequate technology transfer experience and do not network in industrial circles, which results in a huge gap between the concept and the practical result. This research determined the critical success factors and explored the causal relationships influencing the technology transfer from universities. We found that the main impact of the key factors was the technology market dimension. University technology transfer activities had to be classified as top priority. Technology industrial applicability was the main key evaluation factor, along with inventor attitude. In the organizational culture dimension, the attitude and ability of top management were the main evaluation factors. We attempted to draw upon our analysis results to make recommendations related to technology transfer to assist universities in successfully transferring their research results.

show abstract

Deep-Learning-Based Sequence Causal Long-Term Recurrent Convolutional Network for Data Fusion Using Video Data

Jeon

Kim

2023

Electronics

View full text Add to dashboard Cite

The purpose of AI-Based schemes in intelligent systems is to advance and optimize system performance. Most intelligent systems adopt sequential data types derived from such systems. Real-time video data, for example, are continuously updated as a sequence to make necessary predictions for efficient system performance. The majority of deep-learning-based network architectures such as long short-term memory (LSTM), data fusion, two streams, and temporal convolutional network (TCN) for sequence data fusion are generally used to enhance robust system efficiency. In this paper, we propose a deep-learning-based neural network architecture for non-fix data that uses both a causal convolutional neural network (CNN) and a long-term recurrent convolutional network (LRCN). Causal CNNs and LRCNs use incorporated convolutional layers for feature extraction, so both architectures are capable of processing sequential data such as time series or video data that can be used in a variety of applications. Both architectures also have extracted features from the input sequence data to reduce the dimensionality of the data and capture the important information, and learn hierarchical representations for effective sequence processing tasks. We have also adopted a concept of series compact convolutional recurrent neural network (SCCRNN), which is a type of neural network architecture designed for processing sequential data combined by both convolutional and recurrent layers compactly, reducing the number of parameters and memory usage to maintain high accuracy. The architecture is challenge-able and suitable for continuously incoming sequence video data, and doing so allowed us to bring advantages to both LSTM-based networks and CNN-based networks. To verify this method, we evaluated it through a sequence learning model with network parameters and memory that are required in real environments based on the UCF-101 dataset, which is an action recognition data set of realistic action videos, collected from YouTube with 101 action categories. The results show that the proposed model in a sequence causal long-term recurrent convolutional network (SCLRCN) provides a performance improvement of at least 12% approximately or more to be compared with the existing models (LRCN and TCN).

show abstract

Adversarial Optimization-Based Knowledge Transfer of Layer-Wise Dense Flow for Image Classification

Cited by 3 publications

References 28 publications

A New Approach to Neural Network Design for Fast Convergence via Feed-forward Loop

A New Approach to Neural Network Design for Fast Convergence via Feed-forward Loop

Evaluating the Intertwined Relationships of the Drivers for University Technology Transfer

Deep-Learning-Based Sequence Causal Long-Term Recurrent Convolutional Network for Data Fusion Using Video Data

Contact Info

Product

Resources

About