SynergicLearning

Nazemi, Mahdi; Esmaili, Amirhossein; Fayyazi, Arash; Pedram, Massoud

doi:10.1145/3400302.3415696

Cited by 10 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent research in HDC mainly focused on the classification task, aiming to design HDC learning modules for low-power embedded devices. [22,34,65] However, all existing solutions consider the computation power, while communication often dominates the entire energy consumption in IoT systems with low-bandwidth networks. [21] On the other hand, HDM is developed for ultrareliable low-latency communication.…”

Section: Related Workmentioning

confidence: 99%

“…[19] Many academic and industry works have examined HDC to utilize high-dimensional data representation, which is known to be the way the human brain operates. [20][21][22][23][24][25][26][27][28] They showed that HDC offers high robustness in data processing and effectively realizes ML by imitating human cognition with mathematically rigorous vector operations that describe human memory capabilities to store, load, and compare various information. HDC is well suited to address communication and learning challenges in networking systems, as 1) HDC representation is holographic in that it spreads information over high-dimensional components, thus providing strong robustness to noise [27,[29][30][31][32] -a key strength to realize reliable communication, 2) it offers an intuitive and human-interpretable learning process [23] which is computationally efficient to train and highly parallel at heart, [33][34][35][36] and 3) HDC can naturally enable lightweight privacy and security.…”

mentioning

confidence: 99%

See 1 more Smart Citation

NetHD: Neurally Inspired Integration of Communication and Learning in Hyperspace

Poduval,

Ni,

Zou

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

The 6G network, the next‐generation communication system, is envisaged to provide unprecedented experience through hyperconnectivity involving everything. The communication should hold artificial intelligence‐centric network infrastructures as interconnecting a swarm of machines. However, existing network systems use orthogonal modulation and costly error correction code; they are very sensitive to noise and rely on many processing layers. These schemes impose significant overhead on low‐power internet of things devices connected to noisy networks. Herein, a hyperdimensional network‐based system, called , is proposed, which enables robust and efficient data communication/learning. exploits a redundant and holographic representation of hyperdimensional computing (HDC) to design highly robust data modulation, enabling two functionalities on transmitted data: 1) an iterative decoding method that translates the vector back to the original data without error correction mechanisms, or 2) a native hyperdimensional learning technique on transmitted data with no need for costly data decoding. A hardware accelerator that supports both data decoding and hyperdimensional learning using a unified accelerator is also developed. The evaluation shows that provides a bit error rate comparable to that of state‐of‐the‐art modulation schemes while achieving 9.4 faster and 27.8 higher energy efficiency compared to state‐of‐the‐art deep learning systems.

show abstract

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

NetHD: Neurally Inspired Integration of Communication and Learning in Hyperspace

Poduval,

Ni,

Zou

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

Binary Hyperdimensional Computing for Image Encoding

Li¹,

Chen²,

Ji³

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

HDTest: Differential Fuzz Testing of Brain-Inspired Hyperdimensional Computing

Guo

Jiang

et al. 2021

2021 58th ACM/IEEE Design Automation Conference (DAC)

View full text Add to dashboard Cite

Brain-inspired hyperdimensional computing (HDC) is an emerging computational paradigm that mimics brain cognition and leverages hyperdimensional vectors with fully distributed holographic representation and (pseudo)randomness. Compared to other machine learning (ML) methods such as deep neural networks (DNNs), HDC offers several advantages including high energy efficiency, low latency, and one-shot learning, making it a promising alternative candidate on a wide range of applications. However, the reliability and robustness of HDC models have not been explored yet. In this paper, we design, implement, and evaluate HDTest to test HDC model by automatically exposing unexpected or incorrect behaviors under rare inputs. The core idea of HDTest is based on guided differential fuzz testing. Guided by the distance between query hypervector and reference hypervector in HDC, HDTest continuously mutates original inputs to generate new inputs that can trigger incorrect behaviors of HDC model. Compared to traditional ML testing methods, HDTest does not need to manually label the original input. Using handwritten digit classification as an example, we show that HDTest can generate thousands of adversarial inputs with negligible perturbations that can successfully fool HDC models. On average, HDTest can generate around 400 adversarial inputs within one minute running on a commodity computer. Finally, by using the HDTest-generated inputs to retrain HDC models, we can strengthen the robustness of HDC models. To the best of our knowledge, this paper presents the first effort in systematically testing this emerging brain-inspired computational model.

show abstract

SynergicLearning

Cited by 10 publications

References 22 publications

NetHD: Neurally Inspired Integration of Communication and Learning in Hyperspace

NetHD: Neurally Inspired Integration of Communication and Learning in Hyperspace

Binary Hyperdimensional Computing for Image Encoding

HDTest: Differential Fuzz Testing of Brain-Inspired Hyperdimensional Computing

Contact Info

Product

Resources

About