Computer Science

Homeostatic plasticity is a stabilizing mechanism that allows neural systems to maintain their activity around a functional operating point. This is an extremely useful mechanism for neuromorphic computing systems, as it can be used to compensate for chronic shifts, for example due to changes in the network structure. However, it is important that this plasticity mechanism operates on time scales that are much longer than conventional synaptic plasticity ones, in order to not interfere with the learning process. In this paper we present a novel ultra-low leakage cell and an automatic gain control scheme that can adapt the gain of analog log-domain synapse circuits over extremely long time scales. To validate the proposed scheme, we implemented the ultra-low leakage cell in a standard 180 nm Complementary Metal-Oxide-Semiconductor (CMOS) process, and integrated it in an array of dynamic synapses connected to an adaptive integrate and fire neuron. We describe the circuit and demonstrate how it can be configured to scale the gain of all synapses afferent to the silicon neuron in a way to keep the neuron's average firing rate constant around a set operating point. The circuit occupies a silicon area of 84 {\mu}m x 22 {\mu}m and consumes approximately 10.8 nW with a 1.8 V supply voltage. It exhibits time constants of up to 25 kilo-seconds, thanks to a controllable leakage current that can be scaled down to 1.2 atto-Amps (7.5 electrons/s).

In this paper we present a concrete design for a probabilistic (p-) computer based on a network of p-bits, robust classical entities fluctuating between -1 and +1, with probabilities that are controlled through an input constructed from the outputs of other p-bits. The architecture of this probabilistic computer is similar to a stochastic neural network with the p-bit playing the role of a binary stochastic neuron, but with one key difference: there is no sequencer used to enforce an ordering of p-bit updates, as is typically required. Instead, we explore \textit{sequencerless} designs where all p-bits are allowed to flip autonomously and demonstrate that such designs can allow ultrafast operation unconstrained by available clock speeds without compromising the solution's fidelity. Based on experimental results from a hardware benchmark of the autonomous design and benchmarked device models, we project that a nanomagnetic implementation can scale to achieve petaflips per second with millions of neurons. A key contribution of this paper is the focus on a hardware metric − flips per second − as a problem and substrate-independent figure-of-merit for an emerging class of hardware annealers known as Ising Machines. Much like the shrinking feature sizes of transistors that have continually driven Moore's Law, we believe that flips per second can be continually improved in later technology generations of a wide class of probabilistic, domain specific hardware.

Recently, DNA data storage systems have attracted many researchers worldwide. Motivated by the success stories of such systems, in this work we propose a software called BacSoft to clone the data in a bacterial plasmid by using the concept of genetic engineering. We consider the encoding schemes such that it satisfies constraints significant for bacterial data storage.

Backpropagation through nonlinear neurons is an outstanding challenge to the field of optical neural networks and the major conceptual barrier to all-optical training schemes. Each neuron is required to exhibit a directionally dependent response to propagating optical signals, with the backwards response conditioned on the forward signal, which is highly non-trivial to implement optically. We propose a practical and surprisingly simple solution that uses saturable absorption to provide the network nonlinearity. We find that the backward propagating gradients required to train the network can be approximated in a pump-probe scheme that requires only passive optical elements. Simulations show that, with readily obtainable optical depths, our approach can achieve equivalent performance to state-of-the-art computational networks on image classification benchmarks, even in deep networks with multiple sequential gradient approximations. This scheme is compatible with leading optical neural network proposals and therefore provides a feasible path towards end-to-end optical training.

This paper reports on a new method of encapsulating BZ solution droplets in a powder coating of either polyethylene (PE) or polytetrafluoroethylene (PTFE), to produce BZ liquid marbles (LMs). The BZ LMs have solid--liquid interfaces in contrast to the previously reported BZ encapsulation systems used to study pattern formations and wave transfers, such as BZ emulsions and BZ vesicles. All these systems are important to study as they can be seen as analogues for information transfer in excitable systems in nature. Due to the powder coating of the LMs, LMs do not wet the underlying substrate, making the LMs mobile, enabling them to be easily arranged in arrays. The preparation of complex LMs, containing an acidic oscillating solution, proves the resilience of LMs and their application in transporting a wide range of chemical cargoes and in playing a mediating role in chemical reactions. PTFE-coated LMs were harder to prepare and not as robust as PE-coated LMs, therefore oscillation studies of BZ LMs positioned in arrays only focused on PE-coated LMs. Sporadic transfer of excitation waves was observed between LMs placed in close proximity to each other in ordered and disordered arrays, suggesting the transfer of liquid species possibly arises from contact between imperfectly coated areas at the LM--LM interface or capillary action, where solution is actively transported to the marble surface through the coating. Propagation pathways of the excitation waves in both the disordered and ordered arrays of BZ LMs are reported. These results lay the foundations for future studies on information transmission and processing arrays of BZ LMs, in addition to observing BZ wave propagation in a LM and the effect of other physical stimuli such as heat, light and chemical environments on the dynamics of excitation in arrays of BZ Lms.

Numerous neural network circuits and architectures are presently under active research for application to artificial intelligence and machine learning. Their physical performance metrics (area, time, energy) are estimated. Various types of neural networks (artificial, cellular, spiking, and oscillator) are implemented with multiple CMOS and beyond-CMOS (spintronic, ferroelectric, resistive memory) devices. A consistent and transparent methodology is proposed and used to benchmark this comprehensive set of options across several application cases. Promising architecture/device combinations are identified.

This paper presents a study of bifurcation in the time-averaged dynamics of TaO memristors driven by narrow pulses of alternating polarities. The analysis, based on a physics-inspired model, focuses on the stable fixed points and on how these are affected by the pulse parameters. Our main finding is the identification of a driving regime when two stable fixed points exist simultaneously. To the best of our knowledge, such bistability is identified in a single memristor for the first time. This result can be readily tested experimentally, and is expected to be useful in future memristor circuit designs.

The memristive crossbar aims to implement analog weighted neural network, however, the realistic implementation of such crossbar arrays is not possible due to limited switching states of memristive devices. In this work, we propose the design of an analog deep neural network with binary weight update through backpropagation algorithm using binary state memristive devices. We show that such networks can be successfully used for image processing task and has the advantage of lower power consumption and small on-chip area in comparison with digital counterparts. The proposed network was benchmarked for MNIST handwritten digits recognition achieving an accuracy of approximately 90%.

The computational efficiency of the human brain is believed to stem from the parallel information processing capability of neurons with integrated storage in synaptic interconnections programmed by local spike triggered learning rules such as spike timing dependent plasticity (STDP). The extremely low operating voltages (approximately 100 mV) used to trigger neuronal signaling and synaptic adaptation is believed to be a critical reason for the brain's power efficiency. We demonstrate the feasibility of spike triggered STDP behavior in a two-terminal Cu/SiO 2 /W memristive device capable of operating below 500 mV. We analyze the state-dependent nature of conductance updates in the device to develop a phenomenological model. Using the model, we evaluate the potential of such devices to generate precise spike times under supervised learning conditions and classify handwritten digits from the MNIST dataset in an unsupervised learning setting. The results form a promising step towards creating a low power synaptic device capable of on-chip learning.

Genome sequences contain hundreds of millions of DNA base pairs. Finding the degree of similarity between two genomes requires executing a compute-intensive dynamic programming algorithm, such as Smith-Waterman. Traditional von Neumann architectures have limited parallelism and cannot provide an efficient solution for large-scale genomic data. Approximate heuristic methods (e.g. BLAST) are commonly used. However, they are suboptimal and still compute-intensive. In this work, we present BioSEAL, a Biological SEquence ALignment accelerator. BioSEAL is a massively parallel non-von Neumann processing-in-memory architecture for large-scale DNA and protein sequence alignment. BioSEAL is based on resistive content addressable memory, capable of energy-efficient and high-performance associative processing. We present an associative processing algorithm for entire database sequence alignment on BioSEAL and compare its performance and power consumption with state-of-art solutions. We show that BioSEAL can achieve up to 57x speedup and 156x better energy efficiency, compared with existing solutions for genome sequence alignment and protein sequence database search.