Integrated analog neurons inspired by mimicking synapses with metal-oxide memristive devices

Abstract

Artificial neural networks (NNs) integrated with emerging devices are one promising approach to overcoming the limitations of artificial intelligence hardware based on existing CMOS technologies. Two-terminal memristive devices consisting of metal-oxide WOx/MgO were fabricated and investigated in order to add synaptic memory functions to NN hardware. The device showed analog conductance changes similar to a biological synapse’s spike-timing dependent plasticity as well as its binarized characteristics, which depend on waveforms of voltage spikes. To exploit such properties of the memristive devices for practical hardware, NN simulations were executed taking into account analog and binary synapses, resulting in good accuracy. For rapid NN prototyping with resistive synapses, we developed an analog-to-digital mixed circuit with variable resistors, which was fabricated using a standard CMOS process. Thirty-two analog neurons, where 1 neuron comprises 32 synapses, performed 1k synaptic operations at approximately 10 mW and generate neuronal firing at approximately less than 2 μs.

Lithium-ion-Based Resistive Devices of LiCoO2/LiPON/Cu With Ultrathin Interlayers of Titanium Oxide for Neuromorphic Computing

“…Figure 10 shows the STDP results of conductance changes for our LiCoO2/TiOx/LiPON/TiOx/Cu device. In this study, a new shape of the STDP curve were determined to be a hyperbolic tangent (tanh) function-shape, which is contrast with our previous result in memristive devices of metal-oxides [30]. The tanh shape was obtained because, first, the conductance change saturates and becomes constant when the timing is far enough apart because it is determined by the sensitivity of the element to the pulse intensity and time width.…”

“…Figure 11 shows the results of learning with the back propagation method, assuming a typical 3-layer feedforward NN for 16 characters of 16 pixels that can be operated with our previously-developed analog neuromorphic circuit [30]. The simulation in Figure 11 is a numerical simulation assuming 16, 32, 64, 256 and 65536 values (4-, 5-, 6-, 8-and 16-bit equivalent), rather than using the actual device resistance (experimental data, e.g., for 32-value operation) to estimate the cumulative error.…”

Vanadium pentoxide interfacial layer enables high performance all-solid-state thin film batteries

“…Thus, modication of the LiCoO 2 -LiPON interface is regarded as a potential method to enhance the electrochemical performance of LiCoO 2 /LiPON/Li TFBs. 15,16 It was found that a thin protective layer composed of Al 2 O 3 , MgO, or AlF 3 can assist in eliminating the occurrence of interfacial side reactions. [17][18][19] However, their poor mechanical and chemical stability limits their widespread applications.…”

Non-Bernoulli operations of stochastic binary synapses using resistive switching devices for unsupervised learning in a spiking neural network

“…Many attempts have been made to implement STDP in neuromorphic hardware using devices and circuit technology. [12][13][14][15][16][17][18][19][20] One of the most studied devices for this purpose is the memristor. 21) Plastic synaptic weights are represented by the variable conductance of memristors.…”