Abstract: A number of circuits for use in an output block coupled to a non-volatile memory array in a neural network are disclosed. The embodiments include a circuit for converting an output current from a neuron in a neural network into an output voltage, a circuit for converting a voltage received on an input node into an output current, a circuit for summing current received from a plurality of neurons in a neural network, and a circuit for summing current received from a plurality of neurons in a neural network.

Abstract: Numerous examples are disclosed of an artificial neural network comprising a three-dimensional integrated circuit. In one embodiment, a three-dimensional integrated circuit for use in an artificial neural network comprises a first die comprising a first vector by matrix multiplication array and a first input multiplexor, the first die located on a first vertical layer; a second die comprising an input circuit, the second die located on a second vertical layer different than the first vertical layer; and one or more vertical interfaces coupling the first die and the second die; wherein during a read operation, the input circuit provides an input signal to the first input multiplexor over at least one of the one or more vertical interfaces, the first input multiplexor applies the input signal to one or more rows in the first vector by matrix multiplication array, and the first vector by matrix multiplication array generates an output.

Abstract: Numerous examples are disclosed of an artificial neural network comprising a plurality of reference arrays used for configuration of a vector-by-matrix multiplication array. In one example, a system comprises a vector-by-matrix multiplication array in an artificial neural network; and a plurality of reference arrays characterized by different I-V curves, wherein one or more of the plurality of reference arrays are used to generate input voltage the vector-by-matrix multiplication array during operation.

Abstract: In one example, a method is disclosed of compensating for leakage in an array of analog neural non-volatile memory cells, wherein the array is arranged in rows and columns, wherein each row is coupled to a word line and each column is coupled to a bitline, the method comprising measuring leakage for a column of analog neural non-volatile memory cells coupled to a bitline; storing the measured leakage value; and applying the measured leakage value during a read operation of the column of analog neural non-volatile memory cells to compensate for the leakage.

Abstract: A method of forming a device on a silicon substrate having first, second and third areas includes recessing an upper substrate surface in the first and third areas, forming an upwardly extending silicon fin in the second area, forming first source, drain and channel regions in the first area, forming second source, drain and channel regions in the fin, forming third source, drain and channel regions in the third area, forming a floating gate over a first portion of the first channel region using a first polysilicon deposition, forming an erase gate over the first source region and a device gate over the third channel region using a second polysilicon deposition, and forming a word line gate over a second portion of the first channel region, a control gate over the floating gate, and a logic gate over the second channel region using a metal deposition.

Abstract: A method includes recessing an upper surface of a substrate in first and second areas relative to a third area, forming a first conductive layer in the first area, forming a second conductive layer in the three areas, selectively removing the first and second conductive layers in the first area, while maintaining the second conductive layer in the second and third areas, leaving pairs of stack structures in the first area respectively having a control gate of the second conductive layer and a floating gate of the first conductive layer, forming a third conductive layer in the three areas, recessing the upper surface of the third conductive layer below tops of the stack structures and removing the third conductive layer from the second and third areas, removing the second conductive layer from the second and third areas, and forming blocks of metal material in the second and third areas.

Abstract: Numerous embodiments of a precision programming 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: In one example, a method comprises determining a program resolution current value; and setting levels for a programming operation of a plurality of non-volatile memory cells in a neural network array such that a delta current between levels of each pair of adjacent cells in the plurality is a multiple of the program resolution current value.

Abstract: A method of forming a semiconductor device by recessing the upper surface of a semiconductor substrate in first and second areas but not a third area, forming a first conductive layer in the three areas, forming a second conductive layer in all three areas, removing the first and second conductive layers from the second area and portions thereof from the first area resulting in pairs of stack structures each with a control gate over a floating gate, forming a third conductive layer in all three areas, forming a protective layer in the first and second areas and then removing the third conductive layer from the third area, then forming blocks of dummy conductive material in the third area, then etching in the first and second areas to form select and HV gates, and then replacing the blocks of dummy conductive material with blocks of metal material.

Abstract: A method of forming a device on a semiconductor substrate having first, second, third and dummy areas, includes recessing the substrate upper surface in the first, second and dummy areas, forming a first conductive layer over the substrate, removing the first conductive layer from the third area and a second portion of the dummy area, forming a first insulation layer over the substrate, forming first trenches through the first insulation layer and into the substrate in the third area and the second portion of the dummy area, forming second trenches through the first insulation layer, the first conductive layer and into the substrate in the first and second areas and a first portion of the dummy area, and filling the first and second trenches with insulation material. Then, memory cells are formed in the first area, HV devices in the second area and logic devices in the third area.

Abstract: A memory device includes a non-volatile memory cells, source regions and drain regions arranged in rows and columns. Respective ones of the columns of drain regions include first drain regions and second drain regions that alternate with each other. Respective ones of first lines electrically connect together the source regions in one of the rows of the source regions and are electrically isolated from the source regions in other rows of the source regions. Respective ones of second lines electrically connect together the first drain regions of one of the columns of drain regions and are electrically isolated from the second drain regions of the one column of drain regions. Respective ones of third lines electrically connect together the second drain regions of one of the columns of drain regions and are electrically isolated from the first drain regions of the one column of drain regions.

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. In one example, a method for programming a plurality of non-volatile memory cells in an array of non-volatile memory cells, comprises generating a high voltage, and programming a plurality of non-volatile memory cells in an array using the high voltage when a programming enable signal is asserted and providing a feedback loop to maintain the high voltage while programming the plurality of non-volatile memory cells.

Abstract: Numerous embodiments for reading a value stored in a selected memory cell in a vector-by-matrix multiplication (VMM) array in an artificial neural network are disclosed. In one embodiment, an input comprises a set of input bits that result in a series of input pulses applied to a terminal of the selected memory cell, further resulting in a series of output signals that are summed to determine the value stored in the selected memory cell. In another embodiment, an input comprises a set of input bits, where each input bit results in a single pulse or no pulse being applied to a terminal of the selected memory cell, further resulting in a series of output signals which are then weighted according to the binary bit location of the input bit, and where the weighted signals are then summed to determine the value stored in the selected memory cell.

Abstract: A method of scanning N×N pixels using a vector-by-matrix multiplication array by (a) associating a filter of M×M pixels adjacent first vertical and horizontal edges, (b) providing values for the pixels associated with different respective rows of the filter to input lines of different respective N input line groups, (c) shifting the filter horizontally by X pixels, (d) providing values for the pixels associated with different respective rows of the horizontally shifted filter to input lines, of different respective N input line groups, which are shifted by X input lines, (e) repeating steps (c) and (d) until a second vertical edge is reached, (f) shifting the filter horizontally to be adjacent the first vertical edge, and shifting the filter vertically by X pixels, (g) repeating steps (b) through (e) for the vertically shifted filter, and (h) repeating steps (f) and (g) until a second horizontal edge is reached.

Abstract: A simplified method for forming pairs of non-volatile memory cells using two polysilicon depositions. A first polysilicon layer is formed on and insulated from the semiconductor substrate in a first polysilicon deposition process. A pair of spaced apart insulation blocks are formed on the first polysilicon layer. Exposed portions of the first poly silicon layer are removed while maintaining a pair of polysilicon blocks of the first polysilicon layer each disposed under one of the pair of insulation blocks. A second polysilicon layer is formed over the substrate and the pair of insulation blocks in a second polysilicon deposition process. Portions of the second polysilicon layer are removed while maintaining a first polysilicon block (disposed between the pair of insulation blocks), a second polysilicon block (disposed adjacent an outer side of one insulation block), and a third polysilicon block (disposed adjacent an outer side of the other insulation block).

Abstract: Numerous examples are disclosed for an output block coupled to a non-volatile memory array in a neural network and associated methods. In one example, a circuit for converting a current in a neural network into an output voltage comprises a non-volatile memory cell comprises a word line terminal, a bit line terminal, and a source line terminal, wherein the bit line terminal receives the current; and a switch for selectively coupling the word line terminal to the bit line terminal; wherein when the switch is closed, the current flows into the non-volatile memory cell and the output voltage is provided on the bit line terminal.

Abstract: Numerous examples of summing circuits for a neural network are disclosed. In one example, a circuit for summing current received from a plurality of synapses in a neural network comprises a voltage source; a load coupled between the voltage source and an output node; a voltage clamp coupled to the output node for maintaining a voltage at the output node; and a plurality of synapses coupled between the output node and ground; wherein an output current flows through the output node, the output current equal to a sum of currents drawn by the plurality of synapses.

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: Numerous examples are disclosed for verifying a weight programmed into a selected non-volatile memory cell in a neural memory. In one example, a circuit comprises a digital-to-analog converter to convert a target weight comprising digital bits into a target voltage, a current-to-voltage converter to convert an output current from the selected non-volatile memory cell during a verify operation into an output voltage, and a comparator to compare the output voltage to the target voltage during a verify operation.

Abstract: Two or more physical memory cells are grouped together to form a logical cell that stores one of N possible levels. Within each logical cell, the memory cells can be programmed using different mechanisms. For example, one or more of the memory cells in a logical cell can be programmed using a coarse programming mechanism, one or more of the memory cells can be programmed using a fine mechanism, and one or more of the memory cells can be programmed using a tuning mechanism. This achieves extreme programming accuracy and programming speed.