# US 2026/0087338 A1 · Systems and methods for converting an analog machine learning output signal into a digital signal

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0087338 A1
- Document ID: US20260087338A1
- Status: Published application
- Kind: A1
- Application number: 18/892,246
- Filed: 2024-09-20
- Published: 2026-03-26
- Earliest claimed: 2024-09-20
- Assignees: Eva Technology Corp
- Applicants: Eva Technology Corp
- Inventors: Kevin Blaine Anderson; Donald Wood Loomis, III
- Web page: https://patentgrep.com/patent/US20260087338A1

## CPC

- G06N 3/065: Analogue means
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods are disclosed for analog-to-digital-converter (ADC) solutions supporting analog AI deep learning systems. These systems can outperform their digital counterparts in speed and energy efficiency since computations are conducted directly in memory and analog processors inherently support parallel operations. ADCs play a crucial role in analog AI deep learning because they serve as the bridge between the analog and digital worlds. An analog AI deep learning system may comprise a DAC, a programming module, row/column switches, a crossbar array and an ADC. The ADC may comprise switches for time interleaving of an analog neural network output signal, received from the row/column switches associated with the crossbar array. The time interleaved signals are separately ported between two capacitive paths, and are subsequently coupled to separate inverters. A frequency signal is generated by a logic gate, which is coupled to a digital filter that generates an n-bit digital word.

## Claims

### Claim 1

A method for operation of an Analog-to-Digital Converter (ADC) comprising:
receiving an analog neural network output signal from an analog crossbar array network;
time interleaving the analog neural network output signal by a switch module between two separate capacitive paths that are based on a first capacitor and a second capacitor, respectively;
coupling each of the two separate capacitive paths to separate inverters;
generating, by a logic gate, a frequency signal by coupling outputs of the separate inverters to the logic gate; and
generating, by a digital filter, an n-bit digital word proportional to the frequency signal by coupling the frequency signal and a system clock CLK input to the digital filter.

### Claim 2 (depends on 1)

The method of claim 1 wherein,
the analog neural network output signal represents a parallel impedance of the rows and/or columns and is based on programming of each programmable component within the analog crossbar array network.

### Claim 3 (depends on 2)

The method of claim 2 wherein,
the analog neural network output signal has a minimum and maximum value.

### Claim 4 (depends on 1)

The method of claim 1 wherein the separate inverters are hysteresis inverters.

### Claim 5 (depends on 4)

The method of claim 4 wherein when each of the separate inverters are toggled, its input path is reset and an alternate path is released based on the reset and it is allowed to time its own path.

### Claim 6 (depends on 1)

The method of claim 1 further comprising, coupling the outputs of each of the separate inverters to a latch, wherein an output of the latch generates a non-overlapping clock (NCLK) signal that is coupled to a clock device NOV_CLK, wherein outputs of the clock device, NOV_CLK, control the switches.

### Claim 7 (depends on 1)

The method of claim 1, wherein the switch module comprises four switches that generate the time interleaved analog neural network output signals that are coupled to the two separate capacitive paths and coupled to a clock device, NOV_CLK.

### Claim 8 (depends on 1)

The method of claim 1, wherein the logic gate is a NAND gate.

### Claim 9

A system for an Analog-to-Digital Converter (ADC) comprising:
a switch module that receives an analog neural network output signal from an analog crossbar array network and outputs a first time interleaved analog neural network output signal to a first capacitive path and outputs a second time interleaved analog neural network output signal to a second capacitive path;
a first capacitor and a second capacitor, which are separately coupled to the first capacitive path and the second capacitive path, respectively;
a first trigger that receives the first time interleaved analog neural network output signal and a second trigger that receives the second time interleaved analog neural network output signal;
a logic gate that receives the outputs of the first trigger and the second trigger and generates a frequency signal; and
a digital filter that receives the frequency signal and a system clock and generates an n-bit digital word proportional to the frequency signal.

### Claim 10 (depends on 9)

The system of claim 9 wherein the analog neural network output signal is based on programming of a matrix of memristor devices within the analog crossbar array network.

### Claim 11 (depends on 9)

The system of claim 9 wherein the first trigger and the second trigger each comprise a hysteresis inverter.

### Claim 12 (depends on 11)

The system of claim 11 wherein when each of the first trigger and second trigger is toggled, its input path is reset and an alternate path is released based on the reset and it is allowed to time its own path.

### Claim 13 (depends on 9)

The system of claim 9 further comprising a latch that receives the outputs of each of the first trigger and the second trigger, wherein an output of the latch creates a non-overlapping clock (NCLK) signal that is coupled to a clock device, NOV_CLK, wherein outputs of the clock device, NOV_CLK, control the switch module.

### Claim 14 (depends on 9)

The system of claim 9 wherein the logic gate is a NAND gate.

### Claim 15 (depends on 9)

The system of claim 9 wherein the switch module comprises a first switch and a second switch, which generate the first time interleaved analog neural network output signal and the second time interleaved analog neural network output signal.

### Claim 16 (depends on 15)

The system of claim 15 wherein the switch module further comprises a third switch and a fourth switch that receive the first time interleaved analog neural network output signal and the second time interleaved analog neural network output signal and are coupled to a clock device, NOV_CLK.

### Claim 17 (depends on 9)

The system of claim 9, wherein a size of the first capacitor and the second capacitor determines a range and resolution of inner product results for the analog crossbar array network.

### Claim 18 (depends on 9)

The system of claim 9, wherein the digital filter is a Cascaded-Integrated-Comb (CIC) filter that operates without cascading registers.

### Claim 19 (depends on 9)

The system of claim 9, wherein the analog neural network output signal represents a result of a matrix multiplication from the analog crossbar array network.

### Claim 20

A system for an Analog-to-Digital Converter (ADC) for an analog deep learning system comprising:
one or more processors; and
a non-transitory computer-readable medium or media comprising one or more sets of instructions which, when executed by at least one of the one or more processors, causes steps to be performed comprising:
receiving an analog neural network output signal from an analog crossbar array network, wherein the analog neural network output signal is based on programming of a matrix of memristor devices within the analog crossbar array network;
time interleaving the analog neural network output signal by a switch module between two separate capacitive paths based on a first capacitor and a second capacitor, respectively;
coupling each of the two separate capacitive paths to separate inverters;
generating a frequency signal by coupling outputs of the separate inverters to a logic gate; and
generating, by a digital filter, an n-bit digital word proportional to the frequency signal by coupling the frequency signal and a system clock CLK input to the digital filter.
