Improving learning algorithm performance for spiking neural networks

Fu, Qiang; Luo, Yuling; Liu, Junxiu; Bi, Jinjie; Qiu, Senhui; Cao, Yi; Ding, Xuemei

doi:10.1109/icct.2017.8359963

Cited by 11 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past few decades, ANNs have been employed increasingly by more and more researchers, and become an active research area [37][38][39][40]. ANNs have afforded numerous successes with great progress in BC classification and diagnosis in the very early stages [22,[41][42][43][44][45][46][47].…”

Section: Approachesmentioning

confidence: 99%

Machine Learning with Applications in Breast Cancer Diagnosis and Prognosis

Yue

Wang

Chen

et al. 2018

Designs

181

View full text Add to dashboard Cite

Breast cancer (BC) is one of the most common cancers among women worldwide, representing the majority of new cancer cases and cancer-related deaths according to global statistics, making it a significant public health problem in today's society. The early diagnosis of BC can improve the prognosis and chance of survival significantly, as it can promote timely clinical treatment to patients. Further accurate classification of benign tumours can prevent patients undergoing unnecessary treatments. Thus, the correct diagnosis of BC and classification of patients into malignant or benign groups is the subject of much research. Because of its unique advantages in critical features detection from complex BC datasets, machine learning (ML) is widely recognised as the methodology of choice in BC pattern classification and forecast modelling. In this paper, we aim to review ML techniques and their applications in BC diagnosis and prognosis. Firstly, we provide an overview of ML techniques including artificial neural networks (ANNs), support vector machines (SVMs), decision trees (DTs), and k-nearest neighbors (k-NNs). Then, we investigate their applications in BC. Our primary data is drawn from the Wisconsin breast cancer database (WBCD) which is the benchmark database for comparing the results through different algorithms. Finally, a healthcare system model of our recent work is also shown.

show abstract

Section: Approachesmentioning

confidence: 99%

Machine Learning with Applications in Breast Cancer Diagnosis and Prognosis

Yue

Wang

Chen

et al. 2018

Designs

181

View full text Add to dashboard Cite

show abstract

“…"Tensorflow: a system for large-scale machine learning," in 12th USENIX Symposium on Operating Systems Design and Implementation (Savannah, GA: USENIX Association), 265-283. Fu, Q., Luo, Y., Liu, J., Bi, J., Qiu, S., Cao, Y., et al (2017). "Improving learning algorithm performance for spiking neural networks," in 2017 IEEE 17th International Conference on Communication Technology (ICCT) (Chengdu: IEEE), 1916-1919.…”

Section: заключениеmentioning

confidence: 99%

Problems and possibilities of using video analytics in the fields of education and entertainment

Окатьева¹

2021

Management of Education

View full text Add to dashboard Cite

Быстрые изменения и совершенствование технологий произвели революцию в современном мире. Взаимодействие человека и компьютера (HCI) развивалось в течение определенного периода, трансформируя многие аспекты нашей жизни, включая то, как мы учимся. В настоящее время студенты могут извлечь выгоду из быстрого обмена информацией, доступности в Интернете и практической реализации того, что ранее преподавалось только в книгах. Опыт обучения и компетентность зависят от того, насколько хорошо предмет преподается студентам и через какую среду. Книги и текстовые ресурсы со временем зарекомендовали себя как отличный способ доставки и использовались на протяжении веков. Аудио-и видеоматериалы также оказались эффективным способом доставки информации, поскольку они обеспечивают хорошее количество богатого контента за относительно короткий период, что привело к повышению мотивации учащихся в классе и изменению восприятия преподавателей. Однако отсутствие погружения и контроля делает обучение на основе видео менее личным, чем интерактивные классы и моделирование реальной жизни. Видеонаблюдение с помощью видеоаналитики может быть развернуто для мониторинга территорий в определенное время суток. Например, как только школа открывается, не должно быть много активности на парковке или в определенных местах вокруг школы. В таких ситуациях интеллектуальные камеры с видеоаналитикой могут использоваться для обнаружения активности в тех областях, которые представляют интерес, чтобы предупредить службу безопасности школы о том, что что-то может потребовать их внимания. Радиолокационное обнаружение идеально подходит для периметров, где устройство может быть ненавязчиво настроено для оповещения, когда кто-то входит в определенную зону. Rapid changes and improvements in technology have revolutionized the modern world. Human-computer Interaction (HCI) has evolved over a period of time, transforming many aspects of our lives, how we learn. Currently, students can benefit from the rapid exchange of information, accessibility on the Internet, and practical implementation of what was previously taught only in books. Learning experience and competence depend on how well the subject is taught to students and through what medium. Books and text resources have proven to be a great delivery method over time and have been used for centuries. Audio and video materials have also proven to be an effective way to deliver information, as they provide a good amount of rich content in a relatively short period, which has led to increased motivation of students in the classroom and a change in the perception of teachers. However, the lack of immersion and control makes video-based learning less personal than interactive classes and real-life simulations. Video surveillance using video analytics can be deployed to monitor territories at certain times of the day. For example, once a school opens, there shouldn't be a lot of activity in the parking lot or in certain places around the school. In such situations, smart cameras with video analytics can be used to detect activity in areas of interest, to warn the school security service that something may require their attention. Radar detection is ideal for perimeters, where the device can be unobtrusively configured to alert when someone enters a certain area.

show abstract

“…A Support Vector Machine (SVM) and Linear Regression (LR) were used in Wang et al ( 2019 ), but recognition accuracy can be improved. In recent years, deep neural networks (DNN) (Tripathi et al, 2017 ) has been developed into one of the most effective and popular methods in many research fields (Fu et al, 2017 ; Liu et al, 2018a , b , 2019 ; Luo et al, 2018 ). Convolutional Neural Networks (CNN) are widely used in computer vision, image classifications, visual tracking (Danelljan et al, 2016 ), segmentation, and object detections (Girshick et al, 2014 ).…”

Section: Introductionmentioning

confidence: 99%

EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder

Liu

Luo

et al. 2020

Front. Syst. Neurosci.

Self Cite

146

View full text Add to dashboard Cite

Emotion classification based on brain–computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI systems and compared to traditional classification methods improved results have been obtained. In this paper, a novel deep neural network is proposed for emotion classification using EEG systems, which combines the Convolutional Neural Network (CNN), Sparse Autoencoder (SAE), and Deep Neural Network (DNN) together. In the proposed network, the features extracted by the CNN are first sent to SAE for encoding and decoding. Then the data with reduced redundancy are used as the input features of a DNN for classification task. The public datasets of DEAP and SEED are used for testing. Experimental results show that the proposed network is more effective than conventional CNN methods on the emotion recognitions. For the DEAP dataset, the highest recognition accuracies of 89.49% and 92.86% are achieved for valence and arousal, respectively. For the SEED dataset, however, the best recognition accuracy reaches 96.77%. By combining the CNN, SAE, and DNN and training them separately, the proposed network is shown as an efficient method with a faster convergence than the conventional CNN.

show abstract

Improving learning algorithm performance for spiking neural networks

Cited by 11 publications

References 14 publications

Machine Learning with Applications in Breast Cancer Diagnosis and Prognosis

Machine Learning with Applications in Breast Cancer Diagnosis and Prognosis

Problems and possibilities of using video analytics in the fields of education and entertainment

EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder

Contact Info

Product

Resources

About