A 41.3/26.7 pJ per Neuron Weight RBM Processor Supporting On-Chip Learning/Inference for IoT Applications

Chang Hung Tsai*, Wan Ju Yu, Wing Hung Wong, Chen-Yi Lee

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


An energy-efficient restricted Boltzmann machine (RBM) processor (RBM-P) supporting on-chip learning and inference is proposed for machine learning and Internet of Things (IoT) applications in this paper. To train a neural network (NN) model, the RBM structure is applied to supervised and unsupervised learning, and a multi-layer NN can be constructed and initialized by stacking multiple RBMs. Featuring NN model reduction for external memory bandwidth saving, low power neuron binarizer (LPNB) with dynamic clock gating and area-efficient NN-like activation function calculators for power reduction, user-defined connection map (UDCM) for both computation time and bandwidth saving, and early stopping (ES) mechanism for learning process, the proposed system integrates 32 RBM cores with maximal 4k neurons per layer and 128 candidates per sample for machine learning applications. Implemented in 65nm CMOS technology, the proposed RBM-P chip costs 2.2 M gates and 128 kB SRAM with 8.8 mm2 area. Operated at 1.2 V and 210 MHz, this chip achieves 7.53G neuron weights (NWs) and 11.63G NWs per second with 41.3 and 26.7 pJ per NW for learning and inference, respectively.

Original languageEnglish
Article number7967660
Pages (from-to)2601-2612
Number of pages12
JournalIEEE Journal of Solid-State Circuits
Issue number10
StatePublished - 1 Oct 2017


  • Low-power design
  • machine learning
  • memory bandwidth reduction
  • non-linear functions
  • restricted Boltzmann machine (RBM)

Fingerprint Dive into the research topics of 'A 41.3/26.7 pJ per Neuron Weight RBM Processor Supporting On-Chip Learning/Inference for IoT Applications'. Together they form a unique fingerprint.

Cite this