Abstract:
An artificial neural network device that utilizes one or more non-volatile memory arrays as the synapses. The synapses are configured to receive inputs and to generate therefrom outputs. Neurons are configured to receive the outputs. The synapses include a plurality of memory cells, wherein each of the memory cells includes spaced apart source and drain regions formed in a semiconductor substrate with a channel region extending there between, a floating gate disposed over and insulated from a first portion of the channel region and a non-floating gate disposed over and insulated from a second portion of the channel region. Each of the plurality of memory cells is configured to store a weight value corresponding to a number of electrons on the floating gate. The plurality of memory cells are configured to multiply the inputs by the stored weight values to generate the outputs.
Abstract:
A non-volatile memory cell including a semiconductor substrate having a fin shaped upper surface with a top surface and two side surfaces. Source and drain regions are formed in the fin shaped upper surface portion with a channel region there between. A conductive floating gate includes a first portion extending along a first portion of the top surface, and second and third portions extending along first portions of the two side surfaces, respectively. A conductive control gate includes a first portion extending along a second portion of the top surface, second and third portions extending along second portions of the two side surfaces respectively, a fourth portion extending up and over at least some of the floating gate first portion, and fifth and sixth portions extending out and over at least some of the floating gate second and third portions respectively.
Abstract:
The disclosed embodiments comprise a flash memory device that can be configured to operate as a read only memory device. In some embodiments, the flash memory device can be configured into a flash memory portion and a read only memory portion.
Abstract:
The present invention relates to a flash memory system wherein one or more circuit blocks utilize fully depleted silicon-on-insulator transistor design to minimize leakage
Abstract:
Systems and methods are disclosed for providing selective threshold voltage characteristics via use of MOS transistors having differential threshold voltages. In one exemplary embodiment, there is provided a metal oxide semiconductor device comprising a substrate of semiconductor material having a source region, a drain region and a channel region therebetween, an insulating layer over the channel region, and a gate portion of the insulating layer. Moreover, with regard to the device, the shape of the insulating layer and/or the shape or implantation of a junction region are of varied dimension as between the gate-to-drain and gate-to-source junctions to provide differential threshold voltages between them.
Abstract:
A circuit and method are disclosed for operating a non-volatile memory device, comprising time sampling a reference current or voltage in a floating holding node to obtain a hold voltage and applying the hold voltage in sensing circuitry.
Abstract:
A non-volatile memory device comprises a semiconductor substrate of a first conductivity type. An array of non-volatile memory cells is located in the semiconductor substrate and arranged in a plurality of rows and columns. Each memory cell comprises a first region on a surface of the semiconductor substrate of a second conductivity type, and a second region on the surface of the semiconductor substrate of the second conductivity type. A channel region is between the first region and the second region. A word line overlies a first portion of the channel region and is insulated therefrom, and adjacent to the first region and having little or no overlap with the first region. A floating gate overlies a second portion of the channel region, is adjacent to the first portion, and is insulated therefrom and is adjacent to the second region. A coupling gate overlies the floating gate. A bit line is connected to the first region. During the operations of program, read, or erase, a negative voltage can be applied to the word lines and/or coupling gates of the selected or unselected memory cells.
Abstract:
A non-volatile memory cell including a semiconductor substrate having a fin shaped upper surface with a top surface and two side surfaces. Source and drain regions are formed in the fin shaped upper surface portion with a channel region there between. A conductive floating gate includes a first portion extending along a first portion of the top surface, and second and third portions extending along first portions of the two side surfaces, respectively. A conductive control gate includes a first portion extending along a second portion of the top surface, second and third portions extending along second portions of the two side surfaces respectively, a fourth portion extending up and over at least some of the floating gate first portion, and fifth and sixth portions extending out and over at least some of the floating gate second and third portions respectively.