Abstract:
In this paper, we study the effects of sneak paths and parasitic metal line resistance in arrays of CBRAM memristive devices operating as synapses for spiking neural netw...Show MoreMetadata
Abstract:
In this paper, we study the effects of sneak paths and parasitic metal line resistance in arrays of CBRAM memristive devices operating as synapses for spiking neural networks. Three structures of crosspoint array are reviewed: the crossbar (1R), the anode connected matrix (1T-IR) and the cathode connected matrix (1T-IR). We show that the crossbar is an energy-consuming structure with high leakage during SET/RESET and with an increased switching time due to voltage drops along the lines. Furthermore, we show that parasitic line resistance can have a significant impact on the read resistance of the devices, depending on their location in the crossbar.
Date of Conference: 08-10 July 2014
Date Added to IEEE Xplore: 21 August 2014
Electronic ISBN:978-1-4799-6384-3
ISSN Information:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Resistance ,
- Anodes ,
- Cathodes ,
- Mathematical model ,
- Switches ,
- Neurons
- Index Terms
- Neural Network ,
- Spiking Neural Networks ,
- Memristive Devices ,
- Sneak Path ,
- Conductive Bridging Random Access Memory ,
- Voltage Drop ,
- Resistant Parasites ,
- Metal Lines ,
- Synapse ,
- Maximum Size ,
- Pulse Width ,
- Resistance Values ,
- Long-term Potentiation ,
- Worst-case Scenario ,
- Resistance State ,
- Output Neurons ,
- Negative Voltage ,
- Positive Voltage ,
- Long-term Depression ,
- Synaptic Weights ,
- Actual Voltage ,
- Read Mode ,
- Voltage Set ,
- High Resistance State ,
- Electrode Device ,
- Low Resistance State ,
- Conductive Filaments
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Resistance ,
- Anodes ,
- Cathodes ,
- Mathematical model ,
- Switches ,
- Neurons
- Index Terms
- Neural Network ,
- Spiking Neural Networks ,
- Memristive Devices ,
- Sneak Path ,
- Conductive Bridging Random Access Memory ,
- Voltage Drop ,
- Resistant Parasites ,
- Metal Lines ,
- Synapse ,
- Maximum Size ,
- Pulse Width ,
- Resistance Values ,
- Long-term Potentiation ,
- Worst-case Scenario ,
- Resistance State ,
- Output Neurons ,
- Negative Voltage ,
- Positive Voltage ,
- Long-term Depression ,
- Synaptic Weights ,
- Actual Voltage ,
- Read Mode ,
- Voltage Set ,
- High Resistance State ,
- Electrode Device ,
- Low Resistance State ,
- Conductive Filaments