An in-memory computing system for computing vector-matrix multiplications includes an array of resistive memory devices arranged in columns and rows, such that resistive memory devices in each row of the array are interconnected by a respective word line and resistive memory devices in each column of the array are interconnected by a respective bitline. The in-memory computing system also includes an interface circuit electrically coupled to each bitline of the array of resistive memory devices and computes the vector-matrix multiplication between an input vector applied to a given set of word lines and data values stored in the array. For each bitline, the interface circuit receives an output in response to the input being applied to the given wordline, compares the output to a threshold, and increments a count maintained for each bitline when the output exceeds the threshold. The count for a given bitline represents a dot-product.

Techniques for auto weight scaling a bounded weight range of RPU devices with the size of the array during ANN training are provided. In one aspect, a method of ANN training includes: initializing weight values w.sub.init in the array to a random value, wherein the array represents a weight matrix W with m rows and n columns; calculating a scaling factor β based on a size of the weight matrix W; providing digital inputs x to the array; dividing the digital inputs x by a noise and bound management factor α to obtain adjusted digital inputs x′; performing a matrix-vector multiplication of the adjusted digital inputs x′ with the array to obtain digital outputs y′; multiplying the digital outputs y′ by the noise and bound management factor α; and multiplying the digital outputs y′ by the scaling factor β to provide digital outputs y of the array.

A multiply-accumulator (MAC) circuit includes: a plurality of multipliers each comprising: a field-effect transistor configured to apply an intermediate voltage to a node; a pair of resistive devices having resistance values determined based on the intermediate voltage applied to one ends connected to the node and weight setting voltages applied to the other ends; and a capacitor configured to be charged and discharged with an electric charge by receiving a voltage generated in the node based on a combined resistance value of the pair of resistive devices and input voltages applied individually to the other ends of the pair of resistive devices in response to individual resistance values of the pair of resistive devices being determined; and an output line configured to output a voltage based on electric charges charged to and discharged from the plurality of multipliers.

A memory unit with a multiply-accumulate assist scheme for a plurality of multi-bit convolutional neural network based computing-in-memory applications is controlled by a reference voltage, a word line and a multi-bit input voltage. The memory unit includes a non-volatile memory cell, a voltage divider and a voltage keeper. The non-volatile memory cell is controlled by the word line and stores a weight. The voltage divider includes a data line and generates a charge current on the data line according to the reference voltage, and a voltage level of the data line is generated by the non-volatile memory cell and the charge current. The voltage keeper generates an output current on an output node according to the multi-bit input voltage and the voltage level of the data line, and the output current is corresponding to the multi-bit input voltage multiplied by the weight.

A neural network circuit that uses a ramp function as an activation function includes a memory device in which memristors serving as memory elements are connected in a matrix. The neural network circuit further includes I-V conversion amplification circuits for converting currents flowing via the memory elements into voltages, a differential amplifier circuit for performing a differential operation on outputs of two I-V conversion amplification circuits, an A-D converter for performing an A-D conversion on a result of the differential operation, and an output determine that, by referring to input signals of the differential amplifier circuit, determines whether an output signal value of the differential amplifier circuit belongs to an active region or an inactive region. Based on a determination result, the input determiner switches over the differential amplifier circuit and the A-D converter between an operating state and a standby state.

The present invention discloses a computing array based on 1T1R device, operation circuits and operating methods thereof. The computing array has 1T1R arrays and a peripheral circuit; the 1T1R array is configured to achieve operation and storage of an operation result, and the peripheral circuit is configured to transmit data and control signals to control operation and storage processes of the 1T1R arrays; the operation circuits are respectively configured to implement a 1-bit full adder, a multi-bit step-by-step carry adder and optimization design thereof, a 2-bit data selector, a multi-bit carry select adder and a multi-bit pre-calculation adder; and in the operating method corresponding to the operation circuit, initialized resistance states of the 1T1R devices, word line input signals, bit line input signals and source line input signals are controlled to complete corresponding operation and storage processes.

According to an example, discrete-time analog filtering may include receiving an input signal, and sampling the input signal to determine sampled input signal values related to the input signal.

A method of performing a predetermined operation for a circuit that includes a resistor group, one end of the resistor group being configured for connection to a power supply unit, the other end of the resistor group being configured for connection to a sampling capacitor, and a parasitic capacitance existing at each node between resistors of the resistor group. The method includes in a forward process, determining a time when a sampling capacitor voltage applied to the sampling capacitor reaches a first reference voltage as a switching time; at the switching time, connecting the sampling capacitor to a ground or predetermined voltage and floating the power supply unit; in a backward process, after the switching time, determining a time when a power supply unit voltage applied to the power supply unit reaches a second reference voltage as an end time; and performing the predetermined operation based on the end time.

A computer-implemented method for Eigenpair computation is provided. The method includes computing an Eigenvector and respective Eigenvalues of the Eigenvector by using a Stochastic Optimization process. The computing step includes storing the matrix in a Resistive Processing Unit (RPU) crossbar array.

Various arrangements for performing vector-matrix multiplication are provided here. Digital input vectors that include binary-encoded values can be converted into a plurality of analog signals using a plurality of one-bit digital to analog converters (DACs). Using an analog vector matrix multiplier, a vector-matrix multiplication operation can be performed using a weighting matrix for each bit-order of the plurality of analog signals. For each performed vector-matrix multiplication operation, a bit-ordered indication of an output of the analog vector matrix multiplier may be stored. A bit-order weighted summation of the sequentially performed vector-matrix multiplication operation may be performed.