Matches in SemOpenAlex for { <https://semopenalex.org/work/W3103415979> ?p ?o ?g. }
- W3103415979 abstract "Today's applications generate a large amount of data that need to be processed by learning algorithms. In practice, the majority of the data are not associated with any labels. Unsupervised learning, i.e., clustering methods, are the most commonly used algorithms for data analysis. However, running clustering algorithms on traditional cores results in high energy consumption and slow processing speed due to a large amount of data movement between memory and processing units. In this paper, we propose DUAL, a Digital-based Unsupervised learning AcceLeration, which supports a wide range of popular algorithms on conventional crossbar memory. Instead of working with the original data, DUAL maps all data points into high-dimensional space, replacing complex clustering operations with memory-friendly operations. We accordingly design a PIM-based architecture that supports all essential operations in a highly parallel and scalable way. DUAL supports a wide range of essential operations and enables in-place computations, allowing data points to remain in memory. We have evaluated DUAL on several popular clustering algorithms for a wide range of large-scale datasets. Our evaluation shows that DUAL provides a comparable quality to existing clustering algorithms while using a binary representation and a simplified distance metric. DUAL also provides 58.8× speedup and 251.2× energy efficiency improvement as compared to the state-of-the-art solution running on GPU." @default.
- W3103415979 created "2020-11-23" @default.
- W3103415979 creator A5025573294 @default.
- W3103415979 creator A5033221192 @default.
- W3103415979 creator A5036778557 @default.
- W3103415979 creator A5053739677 @default.
- W3103415979 creator A5067380102 @default.
- W3103415979 creator A5079372283 @default.
- W3103415979 date "2020-10-01" @default.
- W3103415979 modified "2023-09-28" @default.
- W3103415979 title "DUAL: Acceleration of Clustering Algorithms using Digital-based Processing In-Memory" @default.
- W3103415979 cites W1159302035 @default.
- W3103415979 cites W1536792390 @default.
- W3103415979 cites W1578783943 @default.
- W3103415979 cites W1857382374 @default.
- W3103415979 cites W1971022913 @default.
- W3103415979 cites W1972648069 @default.
- W3103415979 cites W1975237352 @default.
- W3103415979 cites W1992181154 @default.
- W3103415979 cites W2011430131 @default.
- W3103415979 cites W2013028205 @default.
- W3103415979 cites W2018774711 @default.
- W3103415979 cites W2019397928 @default.
- W3103415979 cites W2022851810 @default.
- W3103415979 cites W2025674646 @default.
- W3103415979 cites W2029205712 @default.
- W3103415979 cites W2036477303 @default.
- W3103415979 cites W2040304075 @default.
- W3103415979 cites W2045915373 @default.
- W3103415979 cites W2049631158 @default.
- W3103415979 cites W2049758109 @default.
- W3103415979 cites W2053744708 @default.
- W3103415979 cites W2057923756 @default.
- W3103415979 cites W2059139185 @default.
- W3103415979 cites W2061071837 @default.
- W3103415979 cites W2066280488 @default.
- W3103415979 cites W2070862086 @default.
- W3103415979 cites W2071965987 @default.
- W3103415979 cites W2081729575 @default.
- W3103415979 cites W2086112773 @default.
- W3103415979 cites W2088340225 @default.
- W3103415979 cites W2094332102 @default.
- W3103415979 cites W2112547256 @default.
- W3103415979 cites W2112796928 @default.
- W3103415979 cites W2118268275 @default.
- W3103415979 cites W2121456247 @default.
- W3103415979 cites W2140405352 @default.
- W3103415979 cites W2141807666 @default.
- W3103415979 cites W2148256155 @default.
- W3103415979 cites W2161160262 @default.
- W3103415979 cites W2167465093 @default.
- W3103415979 cites W2170747616 @default.
- W3103415979 cites W2322020277 @default.
- W3103415979 cites W2331737637 @default.
- W3103415979 cites W2407339173 @default.
- W3103415979 cites W2441968311 @default.
- W3103415979 cites W2476008461 @default.
- W3103415979 cites W2478496062 @default.
- W3103415979 cites W2505929033 @default.
- W3103415979 cites W2508602506 @default.
- W3103415979 cites W2518281301 @default.
- W3103415979 cites W2525637167 @default.
- W3103415979 cites W2605170010 @default.
- W3103415979 cites W2613107232 @default.
- W3103415979 cites W2613567208 @default.
- W3103415979 cites W2613989746 @default.
- W3103415979 cites W2626837834 @default.
- W3103415979 cites W2744849844 @default.
- W3103415979 cites W2752849758 @default.
- W3103415979 cites W2765234579 @default.
- W3103415979 cites W2766489088 @default.
- W3103415979 cites W2773147029 @default.
- W3103415979 cites W2794243109 @default.
- W3103415979 cites W2799942529 @default.
- W3103415979 cites W2801000640 @default.
- W3103415979 cites W2809524490 @default.
- W3103415979 cites W2889160891 @default.
- W3103415979 cites W2894130967 @default.
- W3103415979 cites W2900379535 @default.
- W3103415979 cites W2908843953 @default.
- W3103415979 cites W2909331201 @default.
- W3103415979 cites W2920081941 @default.
- W3103415979 cites W2945707356 @default.
- W3103415979 cites W2949989598 @default.
- W3103415979 cites W2953193622 @default.
- W3103415979 cites W2959627720 @default.
- W3103415979 cites W2962903741 @default.
- W3103415979 cites W2963027573 @default.
- W3103415979 cites W2966470162 @default.
- W3103415979 cites W2983032988 @default.
- W3103415979 cites W2986616285 @default.
- W3103415979 cites W2988640543 @default.
- W3103415979 cites W2996817579 @default.
- W3103415979 cites W2999932424 @default.
- W3103415979 cites W3005783121 @default.
- W3103415979 cites W4236122429 @default.
- W3103415979 cites W4240163901 @default.
- W3103415979 cites W4361787200 @default.
- W3103415979 doi "https://doi.org/10.1109/micro50266.2020.00039" @default.
- W3103415979 hasPublicationYear "2020" @default.