SESOMP: A Scalable and Energy-Efficient Self-Organizing Map Processor with Computing-In-Memory and Dead Neuron Pruning.
Yuncheng LuXin ZhangZehao LiBo WangTony Tae-Hyoung KimPublished in: A-SSCC (2023)
Keyphrases
- self organizing maps
- energy efficient
- neural network
- wireless sensor networks
- multi core architecture
- energy consumption
- sensor networks
- unsupervised learning
- input data
- associative memory
- som neural network
- base station
- routing protocol
- energy efficiency
- data transmission
- memory management
- growing self organizing map
- k means
- high speed
- computer vision
- probabilistic neural network
- single instruction multiple data
- data center
- processing elements
- communication networks
- database
- data processing
- data sets