Training of Quantized Deep Neural Networks using a Magnetic Tunnel Junction-Based Synapse

December 29, 2019 Β· Declared Dead Β· πŸ› Semiconductor Science and Technology

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Tzofnat Greenberg Toledo, Ben Perach, Itay Hubara, Daniel Soudry, Shahar Kvatinsky arXiv ID 1912.12636 Category cs.ET: Emerging Technologies Cross-listed cs.AR, cs.LG, cs.NE Citations 2 Venue Semiconductor Science and Technology Last Checked 3 months ago
Abstract
Quantized neural networks (QNNs) are being actively researched as a solution for the computational complexity and memory intensity of deep neural networks. This has sparked efforts to develop algorithms that support both inference and training with quantized weight and activation values, without sacrificing accuracy. A recent example is the GXNOR framework for stochastic training of ternary (TNN) and binary (BNN) neural networks. In this paper, we show how magnetic tunnel junction (MTJ) devices can be used to support QNN training. We introduce a novel hardware synapse circuit that uses the MTJ stochastic behavior to support the quantize update. The proposed circuit enables processing near memory (PNM) of QNN training, which subsequently reduces data movement. We simulated MTJ-based stochastic training of a TNN over the MNIST, SVHN, and CIFAR10 datasets and achieved an accuracy of 98.61%, 93.99% and 82.71%, respectively (less than 1% degradation compared to the GXNOR algorithm). We evaluated the synapse array performance potential and showed that the proposed synapse circuit can train ternary networks in situ, with 18.3TOPs/W for feedforward and 3TOPs/W for weight update.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Emerging Technologies

Died the same way β€” πŸ‘» Ghosted