No abstract

Dense crossbar arrays of non-volatile memory (NVM) devices represent one possible path for implementing massively-parallel and highly energy-efficient neuromorphic computing systems. We first review recent advances in the application of NVM devices to three computing paradigms: spiking neural networks (SNNs), deep neural networks (DNNs), and 'Memcomputing'. In SNNs, NVM synaptic connections are updated by a local learning rule such as spike-timing-dependent-plasticity, a computational approach directly inspired by biology. For DNNs, NVM arrays can represent matrices of synaptic weights, implementing the matrix-vector multiplication needed for algorithms such as backpropagation in an analog yet massively-parallel fashion. This approach could provide significant improvements in power and speed compared to GPU-based DNN training, for applications of commercial significance. We then survey recent research in which different types of NVM devices-including phase change memory, conductive-bridging RAM, filamentary and nonfilamentary RRAM, and other NVMs-have been proposed, either as a synapse or as a neuron, for use within a neuromorphic computing application. The relevant virtues and limitations of these devices are assessed, in terms of properties such as conductance dynamic range, (non)linearity and (a)symmetry of conductance response, retention, endurance, required switching power, and device variability.

No abstract

There is a significant need to build efficient non-von Neumann computing systems for highly data-centric artificial intelligence related applications. Brain-inspired computing is one such approach that shows significant promise. Memory is expected to play a key role in this form of computing and, in particular, phase-change memory (PCM), arguably the most advanced emerging non-volatile memory technology. Given a lack of comprehensive understanding of the working principles of the brain, brain-inspired computing is likely to be realized in multiple levels of inspiration. In the first level of inspiration, the idea would be to build computing units where memory and processing co-exist in some form. Computational memory is an example where the physical attributes and the state dynamics of memory devices are exploited to perform certain computational tasks in the memory itself with very high areal and energy efficiency. In a second level of brain-inspired computing using PCM devices, one could design a co-processor comprising multiple cross-bar arrays of PCM devices to accelerate the training of deep neural networks. PCM technology could also play a key role in the space of specialized computing substrates for spiking neural networks, and this can be viewed as the third level of brain-inspired computing using these devices.

Recent advances in neuroscience together with nanoscale electronic device technology have resulted in huge interests in realizing brain-like computing hardwares using emerging nanoscale memory devices as synaptic elements. Although there has been experimental work that demonstrated the operation of nanoscale synaptic element at the single device level, network level studies have been limited to simulations. In this work, we demonstrate, using experiments, array level associative learning using phase change synaptic devices connected in a grid like configuration similar to the organization of the biological brain. Implementing Hebbian learning with phase change memory cells, the synaptic grid was able to store presented patterns and recall missing patterns in an associative brain-like fashion. We found that the system is robust to device variations, and large variations in cell resistance states can be accommodated by increasing the number of training epochs. We illustrated the tradeoff between variation tolerance of the network and the overall energy consumption, and found that energy consumption is decreased significantly for lower variation tolerance.