Efficient Data Encoding for Convolutional Neural Network application

Trinh, Hong-Phuc; Duranton, Marc; Paindavoine, Michel

doi:10.1145/2685394

Cited by 12 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to different research objects and application fields, the main research directions of biomedical informatics include the following: Bioinformatics is a discipline that explores objective laws existing in complex biological data according to biological research methods and principles through advanced computer science and technology [ 15 ]. The core problem is to design efficient software or develop more advanced data processing methods for how to organize and understand biological data more effectively [ 16 ].…”

Section: Proposed Methodsmentioning

confidence: 99%

Classification and Reconstruction of Biomedical Signals Based on Convolutional Neural Network

Zhu

Chen

Xie

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The efficient biological signal processing method can effectively improve the efficiency of researchers to explore the work of life mechanism, so as to better reveal the relationship between physiological structure and function, thus promoting the generation of major biological discoveries; high-precision medical signal analysis strategy can, to a certain extent, share the pressure of doctors’ clinical diagnosis and assist them to formulate more favorable plans for disease prevention and treatment, so as to alleviate patients’ physical and mental pain and improve the overall health level of the society. This article in biomedical signal is very representative of the two types of signals: mammary gland molybdenum target X-ray image (mammography) and the EEG signal as the research object, combined with the deep learning field of CNN; the most representative model is two kinds of biomedical signal classification, and reconstruction methods conducted a series of research: (1) a new classification method of breast masses based on multi-layer CNN is proposed. The method includes a CNN feature representation network for breast masses and a feature decision mechanism that simulates the physician’s diagnosis process. By comparing with the objective classification accuracy of other methods for the identification of benign and malignant breast masses, the method achieved the highest classification accuracy of 97.0% under different values of c and gamma, which further verified the effectiveness of the proposed method in the identification of breast masses based on molybdenum target X-ray images. (2) An EEG signal classification method based on spatiotemporal fusion CNN is proposed. This method includes a multi-channel input classification network focusing on spatial information of EEG signals, a single-channel input classification network focusing on temporal information of EEG signals, and a spatial-temporal fusion strategy. Through comparative experiments on EEG signal classification tasks, the effectiveness of the proposed method was verified from the aspects of objective classification accuracy, number of model parameters, and subjective evaluation of CNN feature representation validity. It can be seen that the method proposed in this paper not only has high accuracy, but also can be well applied to the classification and reconstruction of biomedical signals.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Classification and Reconstruction of Biomedical Signals Based on Convolutional Neural Network

Zhu

Chen

Xie

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Accordingly, the related computational logic can be either power/clock gated for the case of ASICs or removed for the case of FPGAs. This is unlike schemes that require a different encoding for each approximate representation [26] or the ones that perform retraining for each accuracy level [17].…”

Section: Caxcnn Methodologymentioning

confidence: 99%

“…Binary (−1, 1) and ternary (−1, 0, 1) networks have been successfully explored in this context [23]- [25]; however, they require specialized retraining procedures to perform the backpropagation. Trinh et al [26] proposed a 7-bit significant position encoding (SPE) scheme to achieve a 12.5 percent storage gain, as compared to an 8-bit fixed point binary representation. The technique made use of differential encoding and weight scaling to represent the filter weights using fewer non-zeros.…”

Section: A State Of the Art And Their Limitationsmentioning

confidence: 99%

CAxCNN: Towards the Use of Canonic Sign Digit Based Approximation for Hardware-Friendly Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

The design of hardware-friendly architectures with low computational overhead is desirable for low latency realization of CNN on resource-constrained embedded platforms. In this work, we propose CAxCNN, a Canonic Sign Digit (CSD) based approximation methodology for representing the filter weights of pre-trained CNNs.The proposed CSD representation allows the use of multipliers with reduced computational complexity. The technique can be applied on top of state-of-the-art CNN quantization schemes in a complementary manner. Our experimental results on a variety of CNNs, trained on MNIST, CIFAR-10 and ImageNet datasets, demonstrate that our methodology provides CNN designs with multiple levels of classification accuracy, without requiring any retraining, and while having a low area and computational overhead. Furthermore, when applied in conjunction with a state-of-art quantization scheme, CAxCNN allows the use of multipliers, which offer 77% logic area reduction, as compared to their accurate counterpart, while incurring a drop in Top-1 accuracy of just 5.63% for a VGG-16 network trained on ImageNet.

show abstract

“…Trinh et al [27] worked on data representation problems, but their analysis is applied to the RTL implementation of the neural networks. In contrast, we promote the use of SLD and high-level programming languages, like SystemC, to validate these aspects at early stages of the design process.…”

Section: Related Workmentioning

confidence: 99%

On the design of scalable and reusable accelerators for big data applications

Pilato

Mantovani

et al. 2016

Proceedings of the ACM International Conference on Computing Frontiers

View full text Add to dashboard Cite

Accelerators are becoming key elements of computing platforms for both data centers and mobile devices as they deliver energyefficient high performance for key computational kernels. However, the design and integration of such components is complex, especially for Big Data applications where they have very large workloads to elaborate. Properly customizing the accelerators' private local memories (PLMs) is of critical importance. To analyze this problem we design an accelerator for Collaborative Filtering by applying a system-level design methodology that allows us to synthesize many alternative micro-architectures as we vary the PLM sizes. We then evaluate the resulting accelerators in terms of resource requirements for both embedded architectures and data centers as we vary the size and density of the workloads.

show abstract

Efficient Data Encoding for Convolutional Neural Network application

Cited by 12 publications

References 25 publications

Classification and Reconstruction of Biomedical Signals Based on Convolutional Neural Network

Classification and Reconstruction of Biomedical Signals Based on Convolutional Neural Network

CAxCNN: Towards the Use of Canonic Sign Digit Based Approximation for Hardware-Friendly Convolutional Neural Networks

On the design of scalable and reusable accelerators for big data applications

Contact Info

Product

Resources

About