FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199832236> ?p ?o ?g. }

• W3199832236 endingPage "897" @default.
• W3199832236 startingPage "877" @default.
• W3199832236 abstract "The application of closed-loop approaches in systems neuroscience and therapeutic stimulation holds great promise for revolutionizing our understanding of the brain and for developing novel neuromodulation therapies to restore lost functions. Neural prostheses capable of multi-channel neural recording, on-site signal processing, rapid symptom detection, and closed-loop stimulation are critical to enabling such novel treatments. However, the existing closed-loop neuromodulation devices are too simplistic and lack sufficient on-chip processing and intelligence. In this paper, we first discuss both commercial and investigational closed-loop neuromodulation devices for brain disorders. Next, we review state-of-the-art neural prostheses with on-chip machine learning, focusing on application-specific integrated circuits (ASIC). System requirements, performance and hardware comparisons, design trade-offs, and hardware optimization techniques are discussed. To facilitate a fair comparison and guide design choices among various on-chip classifiers, we propose a new energy-area (E-A) efficiency figure of merit that evaluates hardware efficiency and multi-channel scalability. Finally, we present several techniques to improve the key design metrics of tree-based on-chip classifiers, both in the context of ensemble methods and oblique structures. A novel Depth-Variant Tree Ensemble (DVTE) is proposed to reduce processing latency (e.g., by 2.5× on seizure detection task). We further develop a cost-aware learning approach to jointly optimize the power and latency metrics. We show that algorithm-hardware co-design enables the energy- and memory-optimized design of tree-based models, while preserving a high accuracy and low latency. Furthermore, we show that our proposed tree-based models feature a highly interpretable decision process that is essential for safety-critical applications such as closed-loop stimulation." @default.
• W3199832236 created "2021-09-27" @default.
• W3199832236 creator A5005963074 @default.
• W3199832236 creator A5011163426 @default.
• W3199832236 creator A5036741715 @default.
• W3199832236 date "2021-10-01" @default.
• W3199832236 modified "2023-10-17" @default.
• W3199832236 title "Closed-Loop Neural Prostheses With On-Chip Intelligence: A Review and a Low-Latency Machine Learning Model for Brain State Detection" @default.
• W3199832236 cites W1567728070 @default.
• W3199832236 cites W1906184128 @default.
• W3199832236 cites W1964974938 @default.
• W3199832236 cites W1967356008 @default.
• W3199832236 cites W1972879677 @default.
• W3199832236 cites W1988790447 @default.
• W3199832236 cites W2004306263 @default.
• W3199832236 cites W2013024221 @default.
• W3199832236 cites W2013754582 @default.
• W3199832236 cites W2017132677 @default.
• W3199832236 cites W2018642663 @default.
• W3199832236 cites W2026263091 @default.
• W3199832236 cites W2040990639 @default.
• W3199832236 cites W2042682017 @default.
• W3199832236 cites W2044628150 @default.
• W3199832236 cites W2047743367 @default.
• W3199832236 cites W2050883281 @default.
• W3199832236 cites W2055559718 @default.
• W3199832236 cites W2078574541 @default.
• W3199832236 cites W2086659790 @default.
• W3199832236 cites W2089035490 @default.
• W3199832236 cites W2091665061 @default.
• W3199832236 cites W2098179667 @default.
• W3199832236 cites W2105425384 @default.
• W3199832236 cites W2108068079 @default.
• W3199832236 cites W2109930285 @default.
• W3199832236 cites W2110565101 @default.
• W3199832236 cites W2119130526 @default.
• W3199832236 cites W2122982148 @default.
• W3199832236 cites W2128682567 @default.
• W3199832236 cites W2132796361 @default.
• W3199832236 cites W2134050473 @default.
• W3199832236 cites W2143685192 @default.
• W3199832236 cites W2143776609 @default.
• W3199832236 cites W2146518537 @default.
• W3199832236 cites W2147851954 @default.
• W3199832236 cites W2154214065 @default.
• W3199832236 cites W2169766445 @default.
• W3199832236 cites W2169812774 @default.
• W3199832236 cites W2171880121 @default.
• W3199832236 cites W2185491959 @default.
• W3199832236 cites W2192749205 @default.
• W3199832236 cites W2278320166 @default.
• W3199832236 cites W2292684827 @default.
• W3199832236 cites W2316516233 @default.
• W3199832236 cites W2317647395 @default.
• W3199832236 cites W2327792914 @default.
• W3199832236 cites W2415653778 @default.
• W3199832236 cites W2463505837 @default.
• W3199832236 cites W2514213849 @default.
• W3199832236 cites W2539070192 @default.
• W3199832236 cites W2586345298 @default.
• W3199832236 cites W2591601611 @default.
• W3199832236 cites W2616997357 @default.
• W3199832236 cites W2622294281 @default.
• W3199832236 cites W2736148182 @default.
• W3199832236 cites W2766983249 @default.
• W3199832236 cites W2767458146 @default.
• W3199832236 cites W2775643054 @default.
• W3199832236 cites W2788344808 @default.
• W3199832236 cites W2790682483 @default.
• W3199832236 cites W2795321524 @default.
• W3199832236 cites W2801605834 @default.
• W3199832236 cites W2802450380 @default.
• W3199832236 cites W2806033632 @default.
• W3199832236 cites W2887044684 @default.
• W3199832236 cites W2890191974 @default.
• W3199832236 cites W2890863075 @default.
• W3199832236 cites W2890963265 @default.
• W3199832236 cites W2891329564 @default.
• W3199832236 cites W2892741787 @default.
• W3199832236 cites W2896520547 @default.
• W3199832236 cites W2897050013 @default.
• W3199832236 cites W2899075265 @default.
• W3199832236 cites W2899212146 @default.
• W3199832236 cites W2899579807 @default.
• W3199832236 cites W2900268635 @default.
• W3199832236 cites W2905175426 @default.
• W3199832236 cites W2905641806 @default.
• W3199832236 cites W2909425830 @default.
• W3199832236 cites W2911964244 @default.
• W3199832236 cites W2912123407 @default.
• W3199832236 cites W2922860987 @default.
• W3199832236 cites W2944985332 @default.
• W3199832236 cites W2948888731 @default.
• W3199832236 cites W2954341676 @default.
• W3199832236 cites W2962700059 @default.
• W3199832236 cites W2968841917 @default.
• W3199832236 cites W2978461629 @default.
• W3199832236 cites W2979410901 @default.

• next