Abstract: The present invention relates to a flash memory cell with only four terminals and decoder circuitry for operating an array of such flash memory cells. The invention allows for fewer terminals for each flash memory cell compared to the prior art, which results in a simplification of the decoder circuitry and overall die space required per flash memory cells. The invention also provides for the use of high voltages on one or more of the four terminals to allow for read, erase, and programming operations despite the lower number of terminals compared to prior art flash memory cells.

Abstract: Numerous embodiments of a precision tuning algorithm and apparatus are disclosed for precisely and quickly depositing the correct amount of charge on the floating gate of a non-volatile memory cell within a vector-by-matrix multiplication (VMM) array in an artificial neural network. Selected cells thereby can be programmed with extreme precision to hold one of N different values.

Abstract: Various embodiments of high voltage generation circuits, high voltage operational amplifiers, adaptive high voltage supplies, adjustable high voltage incrementor, adjustable reference supplies, and reference circuits are disclosed. These circuits optionally can be used for programming a non-volatile memory cell in an analog neural memory to store one of many possible values.

Abstract: A memory device includes a plurality of memory cells and a controller. The controller is configured to program each of the memory cells to one of a plurality of program states, and to read the memory cells using a read operation of applied voltages to the memory cells. During the read operation, separations between adjacent ones of the program states vary based on frequencies of use of the program states in the plurality of memory cells.

Abstract: A neural network device with synapses having memory cells each having source and drain regions in a semiconductor substrate with a channel region extending there between, a floating gate over an entirety of the channel region, and a first gate over the floating gate. First lines each electrically connect together the first gates in one of the memory cell rows, second lines each electrically connect together the source regions in one of the memory cell rows, and third lines each electrically connect together the drain regions in one of the memory cell columns. The synapses are configured to receive a first plurality of inputs as electrical voltages on the first lines or on the second lines, and to provide a first plurality of outputs as electrical currents on the third lines.

Abstract: Various algorithms are disclosed for verifying the stored weight in a non-volatile memory cell in a neural network following a multilevel programming operation of the non-volatile memory cell by converting the stored weight into a plurality of digital output bits. Circuity, such as an adjustable reference current source, for implementing the algorithms are disclosed.

Abstract: Numerous embodiments of power management techniques are disclosed for various operations involving one or more vector-by-matrix multiplication (VMM) arrays within an artificial neural network.

Abstract: Numerous embodiments are disclosed for converting neuron current output by a vector-by-matrix multiplication (VMM) array into neuron current-based time pulses and providing such pulses as an input to another VMM array within an artificial neural network. Numerous embodiments are disclosed for converting the neuron current-based time pulses into analog current or voltage values if an analog input is needed for the VMM array.

Abstract: A neural network device with synapses having memory cells each having a floating gate and a first gate over first and second portions of a channel region disposed between source and drain regions, and a second gate over the floating gate or the source region. First lines each electrically connect the first gates in one of the memory cell rows, second lines each electrically connect the second gates in one of the memory cell rows, third lines each electrically connect the source regions in one of the memory cell columns, and fourth lines each electrically connect the drain regions in one of the memory cell columns. The synapses receive a first plurality of inputs as electrical voltages on the first or second lines, and provide a first plurality of outputs as electrical currents on the third or fourth lines.

Abstract: A memory device includes a plurality of memory cells and a controller. The controller is configured to program each of the memory cells to one of a plurality of program states, and to read the memory cells using a read operation of applied voltages to the memory cells. During the read operation, separations between adjacent ones of the program states vary based on frequencies of use of the program states in the plurality of memory cells.

Abstract: An improved programming technique for non-volatile memory cell arrays, in which memory cells to be programmed with higher programming values are programmed first, and memory cells to be programmed with lower programming values are programmed second. The technique reduces or eliminates the number of previously programmed cells from being adversely incrementally programmed by an adjacent cell being programmed to higher program levels, and reduces the magnitude of adverse incremental programming for most of the memory cells, which is caused by floating gate to floating gate coupling. The memory device includes an array of non-volatile memory cells and a controller configured to identify programming values associated with incoming data, and perform a programming operation in which the incoming data is programmed into at least some of the non-volatile memory cells in a timing order of descending value of the programming values.

Abstract: A neural network device having a first plurality of synapses that includes a plurality of memory cells. Each memory cell includes a floating gate over a first portion of a channel region and a first gate over a second portion of the channel region. The memory cells are arranged in rows and columns. A plurality of first lines each electrically connect together the first gates in one of the memory cell rows, a plurality of second lines each electrically connect together the source regions in one of the memory cell rows, and a plurality of third lines each electrically connect together the drain regions in one of the memory cell columns. The first plurality of synapses receives a first plurality of inputs as electrical voltages on the plurality of third lines, and provides a first plurality of outputs as electrical currents on the plurality of second lines.

Abstract: A system and method are disclosed for performing address fault detection in a flash memory system. In one embodiment, a flash memory system comprises a memory array comprising flash memory cells arranged in rows and columns, a row decoder for receiving a row address as an input, the row decoder coupled to a plurality of word lines, wherein each word line is coupled to a row of flash memory cells in the memory array, an address fault detection array comprising a column of memory cells, wherein each of the plurality of word lines is coupled to a memory cell in the column, and an analog comparator for comparing a current drawn by the column with a reference current and for indicating a fault if the current drawn by the column exceeds the reference current.

Abstract: An improved programming technique for non-volatile memory cell arrays, in which memory cells to be programmed with higher programming values are programmed first, and memory cells to be programmed with lower programming values are programmed second. The technique reduces or eliminates the number of previously programmed cells from being adversely incrementally programmed by an adjacent cell being programmed to higher program levels, and reduces the magnitude of adverse incremental programming for most of the memory cells, which is caused by floating gate to floating gate coupling. The memory device includes an array of non-volatile memory cells and a controller configured to identify programming values associated with incoming data, and perform a programming operation in which the incoming data is programmed into at least some of the non-volatile memory cells in a timing order of descending value of the programming values.

Abstract: A memory device that includes source and drain regions formed in a semiconductor substrate, with a first channel region of the substrate extending there between. A floating gate is disposed over and insulated from the channel region, wherein the conductivity of the channel region is solely controlled by the floating gate. A control gate is disposed over and insulated from the floating gate. An erase gate is disposed over and insulated from the source region, wherein the erase gate includes a notch that faces and is insulated from an edge of the floating gate. Logic devices are formed on the same substrate. Each logic device has source and drain regions with a channel region extending there between, and a logic gate disposed over and controlling the logic device's channel region.

Abstract: A method of forming a memory device that includes forming on a substrate, a first insulation layer, a first conductive layer, a second insulation layer, a second conductive layer, a third insulation layer. First trenches are formed through third insulation layer, the second conductive layer, the second insulation layer and the first conductive layer, leaving side portions of the first conductive layer exposed. A fourth insulation layer is formed at the bottom of the first trenches that extends along the exposed portions of the first conductive layer. The first trenches are filled with conductive material. Second trenches are formed through the third insulation layer, the second conductive layer, the second insulation layer and the first conductive layer. Drain regions are formed in the substrate under the second trenches. A pair of memory cells results, with a single continuous channel region extending between drain regions for the pair of memory cells.

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. Various algorithms for tuning the memory cells to contain the correct weight values are disclosed.

Abstract: Numerous embodiments are disclosed for a high voltage generation algorithm and system for generating high voltages necessary for a particular programming operation in analog neural memory used in a deep learning artificial neural network. Different calibration algorithms and systems are also disclosed. Compensation measures are utilized to compensate for changes in voltage or current as the number of cells being programmed changes.

Abstract: Numerous embodiments of a precision tuning algorithm and apparatus are disclosed for precisely and quickly depositing the correct amount of charge on the floating gate of a non-volatile memory cell within a vector-by-matrix multiplication (VMM) array in an artificial neural network. Selected cells thereby can be programmed with extreme precision to hold one of N different values.

Abstract: Numerous embodiments of an improved charge pump design are disclosed for generating the high voltages necessary to perform erase and program operations in non-volatile flash memory devices. In these embodiments, each boost stage in the charge pump is modified to overcome a deficiency in prior art charge pumps whereby voltage actually would decrease in the final boost stage. These modifications include the addition of one or more of a clock doubling circuit, a local self-precharge circuit, a feed-forward precharge circuit, a feed-backward precharge circuit, and a hybrid circuit comprising NMOS and PMOS transistors and diodes.