Highly Scalable Neuromorphic Hardware with 1-bit Stochastic nano-Synapses

Thermodynamic-driven filament formation in redox-based resistive memory and the impact of thermal fluctuations on switching probability of emerging magnetic switches are probabilistic phenomena in nature, and thus, processes of binary switching in these nonvolatile memories are stochastic and vary from switching cycle-to-switching cycle, in the same device, and from device-to-device, hence, they provide a rich in-situ spatiotemporal stochastic characteristic. This work presents a highly scalable neuromorphic hardware based on crossbar array of 1-bit resistive crosspoints as distributed stochastic synapses. The network shows a robust performance in emulating selectivity of synaptic potentials in neurons of primary visual cortex to the orientation of a visual image. The proposed model could be configured to accept a wide range of nanodevices.

mrPUF: A Memristive Device based Physical Unclonable Function

Physical unclonable functions (PUFs) exploit the intrinsic complexity and irreproducibility of physical systems to generate secret information. PUFs have the potential to provide fundamentally higher security than traditional cryptographic methods by preventing the cloning of identities and the extraction of secret keys. One unique and exciting opportunity is that of using the super-high information content (SHIC) capability of nanocrossbar architecture as well as the high resistance programming variation of resistive memories to develop a highly secure on-chip PUFs for extremely resource constrained devices characterized by limited power and area budgets such as passive Radio Frequency Identification (RFID) devices. We show how to implement PUF based on nano-scale memristive (resistive memory) devices (mrPUF). Our proposed architecture significantly increased the number of possible challenge-response pairs (CRPs), while also consuming relatively lesser power (around 70 uW). The presented approach can be used in other silicon-based PUFs as well.

Memristor-based Synaptic Networks and Logical Operations Using In-Situ Computing

We present new computational building blocks based on memristive devices. These blocks, can be used to implement either supervised or unsupervised learning modules. This is achieved using a crosspoint architecture which is an efficient array implementation for nanoscale two-terminal memristive devices. Based on these blocks and an experimentally verified SPICE macromodel for the memristor, we demonstrate that firstly, the Spike-Timing-Dependent Plasticity (STDP) can be implemented by a single memristor device and secondly, a memristor-based competitive Hebbian learning through STDP using a $1times 1000$ synaptic network. This is achieved by adjusting the memristors conductance values (weights) as a function of the timing difference between presynaptic and postsynaptic spikes. These implementations have a number of shortcomings due to the memristors characteristics such as memory decay, highly nonlinear switching behaviour as a function of applied voltage/current, and functional uniformity. These shortcomings can be addressed by utilising a mixed gates that can be used in conjunction with the analogue behaviour for biomimetic computation. The digital implementations in this paper use in-situ computational capability of the memristor.

Non-volatile Complementary Resistive Switch-based Content Addressable Memory

This paper presents a novel resistive-only Binary and Ternary Content Addressable Memory (B/TCAM) cell that consists of two Complementary Resistive Switches (CRSs). The operation of such a cell relies on a logic$rightarrow$ON state transition that enables this novel CRS application.