摘要:
Embodiments of the present invention provide a device comprising a plurality of phase change memory cells, a word line, and a plurality of bit lines. Each phase change memory cell is coupled to a corresponding transistor. Each transistor is coupled to the word line. Each bit line is coupled to a phase change memory cell of the device. The device further comprises a programming circuit configured to program at least one phase change memory cell to the SET state by selectively applying a two-stage waveform to the word line and the bit lines of the device. In a first stage, a first predetermined low voltage and a first predetermined high voltage are applied at the word line and the bit lines, respectively. In a second stage, a second predetermined high voltage and a predetermined voltage with decreasing amplitude are applied at the word line and the bit lines, respectively.
摘要:
Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor. The source terminal of the transistor device is connected to an axon path, the gate terminal of the transistor device is connected to a membrane path and a second terminal of the variable state resistor is connected to a dendrite path, such that each synaptic device is coupled between a first axon path and a first dendrite path, and between a first membrane path and said first dendrite path.
摘要:
Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor. The source terminal of the transistor device is connected to an axon path, the gate terminal of the transistor device is connected to a membrane path and a second terminal of the variable state resistor is connected to a dendrite path, such that each synaptic device is coupled between a first axon path and a first dendrite path, and between a first membrane path and said first dendrite path.
摘要:
A compact, low-power, asynchronous, resistor-based memory read circuit includes a memory cell having a plurality of consecutive memory states, each of said states corresponding to a respective output voltage. A sense amplifier reads the state of the memory cell. The sense amplifier includes a voltage divider configured to receive the output voltage of the memory cell and to output a settled voltage an amplifier having a voltage threshold between the settled voltages associated with two of said consecutive memory states, configured to discriminate between said two consecutive memory states.
摘要:
A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
摘要:
A compact, low-power, asynchronous, resistor-based memory read circuit includes a memory cell having a plurality of consecutive memory states, each of said states corresponding to a respective output voltage. A sense amplifier reads the state of the memory cell. The sense amplifier includes a voltage divider configured to receive the output voltage of the memory cell and to output a settled voltage an amplifier having a voltage threshold between the settled voltages associated with two of said consecutive memory states, configured to discriminate between said two consecutive memory states.
摘要:
A compact, low-power, asynchronous, resistor-based memory read circuit includes a memory cell having a plurality of consecutive memory states, each of said states corresponding to a respective output voltage. A sense amplifier reads the state of the memory cell. The sense amplifier includes a voltage divider configured to receive the output voltage of the memory cell and to output a settled voltage an amplifier having a voltage threshold between the settled voltages associated with two of said consecutive memory states, configured to discriminate between said two consecutive memory states.
摘要:
A compact, low-power, asynchronous, resistor-based memory read circuit includes a memory cell having a plurality of consecutive memory states, each of said states corresponding to a respective output voltage. A sense amplifier reads the state of the memory cell. The sense amplifier includes a voltage divider configured to receive the output voltage of the memory cell and to output a settled voltage an amplifier having a voltage threshold between the settled voltages associated with two of said consecutive memory states, configured to discriminate between said two consecutive memory states.
摘要:
A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
摘要:
A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.