A static random-access memory (SRAM) system includes SRAM cells configured to perform exclusive NOR operations between a stored binary weight value and a provided binary input value. In some embodiments, SRAM cells are configured to perform exclusive NOR operations between a stored binary weight value and a provided ternary input value. The SRAM cells are suitable for the efficient implementation of emerging deep neural network technologies such as binary neural networks and XNOR neural networks.

Encoding of domain logic rules in an analog content addressable memory (aCAM) is disclosed. By encoding domain logic in an aCAM, rapid and flexible search capabilities are enabled, including the capability to search ranges of analog values, fuzzy match capabilities, and optimized parameter search capabilities. This is achieved with low latency by using only a small number of clock cycles at low power. A domain logic ruleset may be represented using various data structures such as decision trees, directed graphs, or the like. These representations can be converted to a table of values, where each table column can be directly mapped to a corresponding row of the aCAM.

Encoding of domain logic rules in an analog content addressable memory (aCAM) is disclosed. By encoding domain logic in an aCAM, rapid and flexible search capabilities are enabled, including the capability to search ranges of analog values, fuzzy match capabilities, and optimized parameter search capabilities. This is achieved with low latency by using only a small number of clock cycles at low power. A domain logic ruleset may be represented using various data structures such as decision trees, directed graphs, or the like. These representations can be converted to a table of values, where each table column can be directly mapped to a corresponding row of the aCAM.

A track and hold circuit includes a signal input terminal, a clock input terminal, an output terminal, a transistor, and a bootstrapping circuit with a transformer. The transistor includes a source, a drain, and a gate, where the source is coupled to the signal input terminal, and the drain is coupled to the output terminal. The transformer includes a primary winding coupled to the clock input terminal, and a secondary winding. The secondary winding is coupled between the source and the gate to control a gate-source voltage of the transistor.

An analog error correction circuit is disclosed that implements an analog error correction code. The analog circuit includes a crossbar array of memristors or other nonvolatile tunable resistive memory devices. The crossbar array includes a first crossbar array portion programmed with values of a target computation matrix and a second crossbar array portion programmed with values of an encoder matrix for correcting computation errors in the matrix multiplication of an input vector with the computation matrix. The first and second crossbar array portions share the same row lines and are connected to a third crossbar array portion that is programmed with values of a decoder matrix, thereby enabling single-cycle error detection. A computation error is detected based on output of the decoder matrix circuitry and a location of the error is determined via an inverse matrix multiplication operation whereby the decoder matrix output is fed back to the decoder matrix.

Methods, systems, and devices related to a multi-level self-selecting memory device are described. A self-selecting memory cell may store one or more bits of data represented by different threshold voltages of the self-selecting memory cell. A programming pulse may be varied to establish the different threshold voltages by modifying one or more durations during which a fixed level of voltage or fixed level of current is maintained across the self-selecting memory cell. The self-selecting memory cell may include a chalcogenide alloy. A non-uniform distribution of an element in the chalcogenide alloy may determine a particular threshold voltage of the self-selecting memory cell. The shape of the programming pulse may be configured to modify a distribution of the element in the chalcogenide alloy based on a desired logic state of the self-selecting memory cell.

A switch device for switching an analog electrical input signal includes: a switching transistor being a flipped-well-silicon-on-insulator-NMOS transistor; and a bootstrapping arrangement including a voltage providing arrangement for providing a floating voltage during the on-state, wherein the floating voltage is provided at a positive terminal and at a negative terminal of the voltage providing arrangement; wherein the bootstrapping arrangement is configured in such way that during the on-state the positive terminal is electrically connected to the front gate contact of the switching transistor and to the back gate contact of the switching transistor, and the negative terminal is electrically connected to the source contact of the switching transistor; wherein the bootstrapping arrangement is configured in such way that during the off-state the positive terminal and the negative terminal are not electrically connected to the switching transistor.

An analog memory device includes a first node and a second node. The first node includes a first floating gate, a second floating gate, and a capacitor. The first node first floating gate is connected to the first node second floating gate via the capacitor. The second node includes a first floating gate, a second floating gate, and a capacitor. The second node first floating gate is connected to the second node second floating gate via the capacitor. The second node is connected to the first node, and an analog state of the first node and an analog state of the second node continuously and synchronously decay with respect to time.

Systems and methods for a capacitor based resistive processing unit with symmetrical weight updating include a first capacitor that stores a charge corresponding to a weight value. A readout circuit reads the charge stored in the first capacitor to apply a weight to an input value corresponding to an input signal using the weight value to produce an output. An update circuit updates the weight value stored in the first capacitor, including a second capacitor in communication with the first capacitor to transfer an amount of charge to the first capacitor according to an error of the output by changing a voltage difference across the first capacitor by a voltage change corresponding to the amount of charge, the voltage difference corresponding to the charge stored in the first capacitor.

A static random-access memory (SRAM) system includes SRAM cells configured to perform exclusive NOR operations between a stored binary weight value and a provided binary input value. In some embodiments, SRAM cells are configured to perform exclusive NOR operations between a stored binary weight value and a provided ternary input value. The SRAM cells are suitable for the efficient implementation of emerging deep neural network technologies such as binary neural networks and XNOR neural networks.