Open Access selected Papers

IEEE Open Access

IEEE Transactions on Emerging Topics in Computational Intelligence now offers publication of its highlighted papers in Open Access for the duration of 3 months in order to assist authors gain maximum exposure for their groundbreaking research and application-oriented papers to all reader communities.

The third highlighted paper offered to make Open Access in TETCI is now available for the duration of 3 months starting from 1 July 2019.


An All-Memristor Deep Spiking Neural Computing System: A Step Toward Realizing the Low-Power Stochastic Brain
Authors: Parami Wijesinghe, Aayush Ankit, Abhronil Sengupta and Kaushik Roy
Publication: IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)
Issue: Volume 2, Issue 5 – October 2018
Pages: 345-358

Abstract: Deep analog artificial neural networks (ANNs) perform complex classification problems with remarkably high accuracy. However, they rely on humongous amount of power to perform the calculations, veiling the accuracy benefits. The biological brain, on the other hand, is significantly more powerful than such networks and consumes orders of magnitude less power, indicating us about some conceptual mismatch. Given that the biological neurons communicate using energy efficient trains of spikes, and the behavior is nondeterministic, incorporating these effects in deep artificial neural networks may drive us few steps toward a more realistic neuron. In this paper, we propose how the inherent stochasticity of nanoscale resistive devices can be harnessed to emulate the functionality of a spiking neuron that can be incorporated in deep stochastic spiking neural networks (SNN). At the algorithmic level, we propose how the training can be modified to convert an ANN to an SNN while supporting the stochastic activation function offered by these devices. We devise circuit architectures to incorporate stochastic memristive neurons along with memristive crossbars, which perform the functionality of the synaptic weights. We tested the proposed all-memristor deep stochastic SNN for image classification and observed only about 1% degradation in accuracy with the ANN baseline after incorporating the circuit and device related nonidealities. We witnessed that the network is robust to certain variations and consumes ~6.4 x less energy than its complementary metal oxide semiconductor (CMOS) counterpart.

Index Terms: Memristor, Stochasticity, Deep stochastic spiking neural networks
IEEE Xplore Link: https://ieeexplore.ieee.org/document/8471280


Available in Open Access from 1 July 2019 to 30 September 2019 in IEEE Xplore Digital Library.


Previous Open Access selected Papers

Light Gated Recurrent Units for Speech Recognition
Authors: Mirco Ravanelli, Philemon Brakel, Maurizio Omologo and Yoshua Bengio
Publication: IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)
Issue: Volume 2, Issue 2 – April 2018
Pages: 92-102
Index Terms: Speech recognition, Deep learning, Recurrent neural networks, LSTM, GRU
IEEE Xplore Link: https://ieeexplore.ieee.org/document/8323308

End-to-End Learning for Physics-Based Acoustic Modeling
Authors: Leonardo Gabrielli, Stefano Tomassetti, Carlo Zinato and Francesco Piazza
Publication: IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)
Issue: Volume 2, Issue 2 – April 2018
Pages: 160-170
Index Terms: Physics-based acoustic modeling, End-to-end learning, Convolutional neural networks
IEEE Xplore Link: https://ieeexplore.ieee.org/document/8323323