Sean C. Smithson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sean C. Smithson has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Warren J. Gross
McGill University
4 shared publications Brett H. Meyer
Department of Electrical and Computer Engineering, McGill University, Montreal, QC H3A 0E9, Canada
3 shared publications- Naoya Onizawa
Tohoku University
3 shared publications - Takahiro Hanyu
Tohoku University
2 shared publications Arash Ardakani
1 shared publication- Brett H. Meyer
McGill University
1 shared publication
Latest Publications
- Open Access
- 22 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 40 (4) , 655-665
A Design Framework for Invertible Logic
Invertible logic using a probabilistic magnetoresistive device model has been recently presented that can compute functions in bidirectional ways and solve several problems quickly, such as factorization and combinational optimization. In this paper, we present a design framework for invertible logic circuits. Our approach makes use of linear programming to create a Hamiltonian library with the minimum number of nodes for small invertible-logic functions In addition, as the device model is approximated based on stochastic computing in synthesizable SystemVerilog, a faster simulation using the compiled SystemC binary is realized than a conventional SPICE-level simulation and is verified using field-programmable gate array (FPGA) as prototyping. Using our design framework, several invertible-logic circuits are designed and emulated (verified) in SystemC, exhibiting five order-of-magnitude faster simulation than a conventional work.
- 22 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 40 (4) , 655-665
Open AccessA Design Framework for Invertible Logic
Invertible logic using a probabilistic magnetoresistive device model has been recently presented that can compute functions in bidirectional ways and solve several problems quickly, such as factorization and combinational optimization. In this paper, we present a design framework for invertible logic circuits. Our approach makes use of linear programming to create a Hamiltonian library with the minimum number of nodes for small invertible-logic functions In addition, as the device model is approximated based on stochastic computing in synthesizable SystemVerilog, a faster simulation using the compiled SystemC binary is realized than a conventional SPICE-level simulation and is verified using field-programmable gate array (FPGA) as prototyping. Using our design framework, several invertible-logic circuits are designed and emulated (verified) in SystemC, exhibiting five order-of-magnitude faster simulation than a conventional work.
- 31 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 67 (5) , 1541-1550
In-Hardware Training Chip Based on CMOS Invertible Logic for Machine Learning
Deep Neural Networks (DNNs) have recently shown state-of-the-art results on various applications, such as computer vision and recognition tasks. DNN inference engines can be implemented in hardware with high energy efficiency as the computation can be realized using a low-precision fixed point or even binary precision with sufficient cognition accuracies. On the other hand, training DNNs using the well-known back-propagation algorithm requires high-precision floating-point computations on a CPU and/or GPU causing significant power dissipation (more than hundreds of kW) and long training time (several days or more). In this paper, we demonstrate a training chip fabricated using a commercial 65-nm CMOS technology for machine learning. The chip performs training without back propagation by using invertible logic with stochastic computing that can directly obtain weight values using input/output training data with low precision suitable for inference. When training neurons that compute the weighted sum of all inputs and then apply a non-linear activation function, our chip demonstrates a reduction of power dissipation and latency by 99.98% and 99.95%, respectively, in comparison with a state-of-the-art software implementation.
- 31 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 67 (5) , 1541-1550
In-Hardware Training Chip Based on CMOS Invertible Logic for Machine Learning
Deep Neural Networks (DNNs) have recently shown state-of-the-art results on various applications, such as computer vision and recognition tasks. DNN inference engines can be implemented in hardware with high energy efficiency as the computation can be realized using a low-precision fixed point or even binary precision with sufficient cognition accuracies. On the other hand, training DNNs using the well-known back-propagation algorithm requires high-precision floating-point computations on a CPU and/or GPU causing significant power dissipation (more than hundreds of kW) and long training time (several days or more). In this paper, we demonstrate a training chip fabricated using a commercial 65-nm CMOS technology for machine learning. The chip performs training without back propagation by using invertible logic with stochastic computing that can directly obtain weight values using input/output training data with low precision suitable for inference. When training neurons that compute the weighted sum of all inputs and then apply a non-linear activation function, our chip demonstrates a reduction of power dissipation and latency by 99.98% and 99.95%, respectively, in comparison with a state-of-the-art software implementation.
- 11 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 66 (6) , 2263-2274
Efficient CMOS Invertible Logic Using Stochastic Computing
Invertible logic can operate in one of two modes: 1) a forward mode, in which inputs are presented and a single, correct output is produced, and 2) a reverse mode, in which the output is fixed and the inputs take on values consistent with the output. It is possible to create invertible logic using various Boltzmann machine configurations. Such systems have been shown to solve certain challenging problems quickly, such as factorization and combinatorial optimization. In this paper, we show that invertible logic can be implemented using simple spiking neural networks based on stochastic computing. We present a design methodology for invertible stochastic gates, which can be implemented using a small amount of CMOS hardware. We demonstrate that our design can not only correctly implement the basic gates with invertible capability but can also be extended to construct invertible stochastic adder and multiplier circuits. The experimental results are presented, which demonstrate the correct operation of synthesizable invertible circuitry performing both multiplication and factorization, along with fabricated ASIC measurement results for an invertible multiplier circuit.
- 11 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 66 (6) , 2263-2274
Efficient CMOS Invertible Logic Using Stochastic Computing
Invertible logic can operate in one of two modes: 1) a forward mode, in which inputs are presented and a single, correct output is produced, and 2) a reverse mode, in which the output is fixed and the inputs take on values consistent with the output. It is possible to create invertible logic using various Boltzmann machine configurations. Such systems have been shown to solve certain challenging problems quickly, such as factorization and combinatorial optimization. In this paper, we show that invertible logic can be implemented using simple spiking neural networks based on stochastic computing. We present a design methodology for invertible stochastic gates, which can be implemented using a small amount of CMOS hardware. We demonstrate that our design can not only correctly implement the basic gates with invertible capability but can also be extended to construct invertible stochastic adder and multiplier circuits. The experimental results are presented, which demonstrate the correct operation of synthesizable invertible circuitry performing both multiplication and factorization, along with fabricated ASIC measurement results for an invertible multiplier circuit.
- 1 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 309-314
Stochastic Computing Can Improve Upon Digital Spiking Neural Networks
With the surge in popularity of machine learning algorithms, research has turned towards exploring novel computing architectures in order to increase performance while limiting power consumption. Inspired by their biological counterparts, digital spiking neural networks have emerged as energy efficient alternatives to conventional hardware implementations, yet remain largely incompatible with cutting edge learning methods. Representing information with single-bit binary pulse trains, the behaviour of spiking neural networks exhibit many interesting analogues to the existing field of stochastic computing. In this paper, we not only illustrate the parallels between digital spiking neural networks and stochastic computing, but we also demonstrate that many computing elements in modern spiking hardware are, in fact, implementations of stochastic circuits. In addition, we show that stochastic computing design techniques can be leveraged in order to address shortcomings in current spiking neural network architectures.
- 1 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 309-314
Stochastic Computing Can Improve Upon Digital Spiking Neural Networks
With the surge in popularity of machine learning algorithms, research has turned towards exploring novel computing architectures in order to increase performance while limiting power consumption. Inspired by their biological counterparts, digital spiking neural networks have emerged as energy efficient alternatives to conventional hardware implementations, yet remain largely incompatible with cutting edge learning methods. Representing information with single-bit binary pulse trains, the behaviour of spiking neural networks exhibit many interesting analogues to the existing field of stochastic computing. In this paper, we not only illustrate the parallels between digital spiking neural networks and stochastic computing, but we also demonstrate that many computing elements in modern spiking hardware are, in fact, implementations of stochastic circuits. In addition, we show that stochastic computing design techniques can be leveraged in order to address shortcomings in current spiking neural network architectures.