Computer Science

Probabilistic machine learning enabled by the Bayesian formulation has recently gained significant attention in the domain of automated reasoning and decision-making. While impressive strides have been made recently to scale up the performance of deep Bayesian neural networks, they have been primarily standalone software efforts without any regard to the underlying hardware implementation. In this paper, we propose an "All-Spin" Bayesian Neural Network where the underlying spintronic hardware provides a better match to the Bayesian computing models. To the best of our knowledge, this is the first exploration of a Bayesian neural hardware accelerator enabled by emerging post-CMOS technologies. We develop an experimentally calibrated device-circuit-algorithm co-simulation framework and demonstrate 24× reduction in energy consumption against an iso-network CMOS baseline implementation.

A time-domain analog-weighted-sum calculation model based on a pulse-width modulation (PWM) approach is proposed. The proposed calculation model can be applied to any types of network structure including multi-layer feedforward networks. We also propose very large-scale integrated (VLSI) circuits to implement the proposed model. Unlike the conventional analog voltage or current mode circuits used in computing-in-memory circuits, our time-domain analog circuits use transient operation in charging/discharging processes to capacitors. Since the circuits can be designed without operational amplifiers, they can be operated with extremely low power consumption. However, they have to use very high-resistance devices, on the order of giga-ohms. We designed a CMOS VLSI chip to verify weighted-sum operation based on the proposed model with binary weights, which realizes the BinaryConnect model. In the chip, memory cells of static-random-access memory (SRAM) are used for synaptic connection weights. High-resistance operation was realized by using the subthreshold operation region of MOS transistors unlike the ordinary computing-in-memory circuits. The chip was designed and fabricated using a 250-nm fabrication technology. Measurement results showed that energy efficiency for the weighted-sum calculation was 300~TOPS/W (Tera-Operations Per Second per Watt), which is more than one order of magnitude higher than that in state-of-the-art digital AI processors, even though the minimum width of interconnection used in this chip was several times larger than that in such digital processors. If state-of-the-art VLSI technology is used to implement the proposed model, an energy efficiency of more than 1,000~TOPS/W will be possible. For practical applications, development of emerging analog memory devices such as ferroelectric-gate field effect transistors (FeFETs) is necessary.

Spiking Neural Networks (SNN) represent a biologically inspired computation model capable of emulating neural computation in human brain and brain-like structures. The main promise is very low energy consumption. Unfortunately, classic Von Neumann architecture based SNN accelerators often fail to address demanding computation and data transfer requirements efficiently at scale. In this work, we propose a promising alternative, an in-memory SNN accelerator based on Spintronic Computational RAM (CRAM) to overcome scalability limitations, which can reduce the energy consumption by up to 164.1\times when compared to a representative ASIC solution.

Software-defined metasurfaces (SDMs) comprise a dense topology of basic elements called meta-atoms, exerting the highest degree of control over surface currents among intelligent panel technologies. As such, they can transform impinging electromagnetic (EM) waves in complex ways, modifying their direction, power, frequency spectrum, polarity and phase. A well-defined software interface allows for applying such functionalities to waves and inter-networking SDMs, while abstracting the underlying physics. A network of SDMs deployed over objects within an area, such as a floorplan walls, creates programmable wireless environments (PWEs) with fully customizable propagation of waves within them. This work studies the use of machine learning for configuring such environments to the benefit of users within. The methodology consists of modeling wireless propagation as a custom, interpretable, back-propagating neural network, with SDM elements as nodes and their cross-interactions as links. Following a training period the network learns the propagation basics of SDMs and configures them to facilitate the communication of users within their vicinity.

The high computation and memory storage of large deep neural networks (DNNs) models pose intensive challenges to the conventional Von-Neumann architecture, incurring substantial data movements in the memory hierarchy. The memristor crossbar array has emerged as a promising solution to mitigate the challenges and enable low-power acceleration of DNNs. Memristor-based weight pruning and weight quantization have been seperately investigated and proven effectiveness in reducing area and power consumption compared to the original DNN model. However, there has been no systematic investigation of memristor-based neuromorphic computing (NC) systems considering both weight pruning and weight quantization. In this paper, we propose an unified and systematic memristor-based framework considering both structured weight pruning and weight quantization by incorporating alternating direction method of multipliers (ADMM) into DNNs training. We consider hardware constraints such as crossbar blocks pruning, conductance range, and mismatch between weight value and real devices, to achieve high accuracy and low power and small area footprint. Our framework is mainly integrated by three steps, i.e., memristor-based ADMM regularized optimization, masked mapping and retraining. Experimental results show that our proposed framework achieves 29.81X (20.88X) weight compression ratio, with 98.38% (96.96%) and 98.29% (97.47%) power and area reduction on VGG-16 (ResNet-18) network where only have 0.5% (0.76%) accuracy loss, compared to the original DNN models. We share our models at link this http URL.

Neuromorphic systems typically employ current-mode circuits that model neural dynamics and produce output currents that range from few pico-Amperes to hundreds of micro-Amperes. On-line real-time monitoring of the signals produced by these circuits is crucial, for prototyping and debugging purposes, as well as for analyzing and understanding the network dynamics and computational properties. To this end, we propose a compact on-chip auto-scaling Current to Frequency Converter (CFC) for real-time monitoring of analog currents in mixed-signal/analog neuromorphic electronic systems. The proposed CFC is a self-timed asynchronous circuit that has a wide dynamic input range of up to 6 decades, ranging from pico-Amps to micro-Amps, with high current measurement sensitivity. To produce a linear output frequency response, while properly covering the wide dynamic input range, the circuit automatically detects the scale of the input current and adjusts the scale of its output firing rate accordingly. Here we describe the proposed circuit and present experimental results measured from multiple instances of the circuit, implemented using a standard 180 nm CMOS process, and interfaced to silicon neuron and synapse circuits for real-time current monitoring. We demonstrate how the circuit is suitable for measuring neural dynamics by showing the converted response properties of the chip silicon neurons and synapses as they are stimulated by input spikes.

Recently, the development of quantum chips has made great progress-- the number of qubits is increasing and the fidelity is getting higher. However, qubits of these chips are not always fully connected, which sets additional barriers for implementing quantum algorithms and programming quantum programs. In this paper, we introduce a general circuit optimizing scheme, which can efficiently adjust and optimize quantum circuits according to arbitrary given qubits' layout by adding additional quantum gates, exchanging qubits and merging single-qubit gates. Compared with the optimizing algorithm of IBM's QISKit, the quantum gates consumed by our scheme is 74.7%, and the execution time is only 12.9% on average.

Smaller, smarter and faster edge devices in the Internet of things era demands secure data analysis and transmission under resource constraints of hardware architecture. Lightweight cryptography on edge hardware is an emerging topic that is essential to ensure data security in near-sensor computing systems such as mobiles, drones, smart cameras, and wearables. In this article, the current state of memristive cryptography is placed in the context of lightweight hardware cryptography. The paper provides a brief overview of the traditional hardware lightweight cryptography and cryptanalysis approaches. The contrast for memristive cryptography with respect to traditional approaches is evident through this article, and need to develop a more concrete approach to developing memristive cryptanalysis to test memristive cryptographic approaches is highlighted.

Neural processing systems typically represent data using leaky integrate and fire (LIF) neuron models that generate spikes or pulse trains at a rate proportional to their input amplitudes. This mechanism requires high firing rates when encoding time-varying signals, leading to increased power consumption. Neuromorphic systems that use adaptive LIF neuron models overcome this problem by encoding signals in the relative timing of their output spikes rather than their rate. In this paper, we analyze recent adaptive LIF neuron circuit implementations and highlight the analogies and differences between them and a first-order sigma-delta feedback loop. We propose a new sigma-delta neuron circuit that addresses some of the limitations in existing implementations and present simulation results that quantify the improvements. We show that the new circuit, implemented in a 1.8 V, 180 nm CMOS process, offers up to 42 dB signal-to-distortion ratio and consumes orders of magnitude lower energy. Finally, we also demonstrate how the sigma-delta interpretation enables mapping of real-valued recurrent neural network to the spiking framework to emphasize the envisioned application of the proposed circuit.

Developing mixed-signal analog-digital neuromorphic circuits in advanced scaled processes poses significant design challenges. We present compact and energy efficient sub-threshold analog synapse and neuron circuits, optimized for a 28 nm FD-SOI process, to implement massively parallel large-scale neuromorphic computing systems. We describe the techniques used for maximizing density with mixed-mode analog/digital synaptic weight configurations, and the methods adopted for minimizing the effect of channel leakage current, in order to implement efficient analog computation based on pA-nA small currents. We present circuit simulation results, based on a new chip that has been recently taped out, to demonstrate how the circuits can be useful for both low-frequency operation in systems that need to interact with the environment in real-time, and for high-frequency operation for fast data processing in different types of spiking neural network architectures.