Configurable Kernel Map Implementation in Memristor Crossbar for Convolution Neural Network
A configurable kernel map implementation using a memristor crossbar array is presented. The crossbar array area can be configured based on the number of read cycles per inference, which directly affects the inference speed. The algorithm underlying this scheme is described, and convolutional neural network operations are experimentally validated using ...
Gyeonghae Kim+3 more
wiley +1 more source
Learning Vector Quantization with Training Count (LVQTC) [PDF]
R. Odorico
openalex +1 more source
Reprogrammable, In‐Materia Matrix‐Vector Multiplication with Floppy Modes
This article describes a metamaterial that mechanically computes matrix‐vector multiplications, one of the fundamental operations in artificial intelligence models. The matrix multiplication is encoded in floppy modes, near‐zero force deformations of soft matter systems.
Theophile Louvet+2 more
wiley +1 more source
Improving Long‐Term Glucose Prediction Accuracy with Uncertainty‐Estimated ProbSparse‐Transformer
Wearable devices collect blood glucose and other physiological data, which serve as inputs to the prediction model. After data embedding, a structure utilizing ProbSparse self‐attention and a one‐step generative head within a Transformer‐based model is introduced, which is concurrently designed for deployment on edge devices, enabling real‐time ...
Wei Huang+5 more
wiley +1 more source
Learning vector quantization as an interpretable classifier for the detection of SARS-CoV-2 types based on their RNA sequences. [PDF]
Kaden M+6 more
europepmc +1 more source
Lower bound on the mean-squared error in oversampled quantization of periodic signals using vector quantization analysis [PDF]
N.T. Thao, Martin Vetterli
openalex +1 more source
Laurenz Wiskott
semanticscholar +1 more source
Symbolic Reservoir Computing within Memristive Crossbar Arrays as a Cellular Automata
In quest of a neuro‐symbolic system with both strong intelligent computing capability and better explainability, a memristor crossbar array‐based cellular automata (symbolic model) for reservoir computing (neural network) is proposed and experimentally demonstrated using an algorithm–hardware codesign approach.
Yunpeng Guo+8 more
wiley +1 more source
A self-organizing world: special issue of the 13th edition of the workshop on self-organizing maps and learning vector quantization, clustering and data visualization, WSOM + 2019. [PDF]
Vellido A, Angulo C, Gibert K.
europepmc +1 more source
Joint image compression and classification with vector quantization and a two dimensional hidden Markov model [PDF]
Jingtao Li+2 more
openalex +1 more source