# US 2026/0065057 A1 · Latent feature activity constraints for ensuring explainability in interpretable neural network models

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

- Number: US 2026/0065057 A1
- Document ID: US20260065057A1
- Status: Published application
- Kind: A1
- Application number: 18/917,370
- Filed: 2024-10-16
- Published: 2026-03-05
- Earliest claimed: 2024-08-29
- Assignees: Fair Isaac Corporation
- Applicants: Fair Isaac Corporation
- Inventors: Scott Michael Zoldi; Krzysztof Nalborski
- Web page: https://patentgrep.com/patent/US20260065057A1

## CPC

- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/048: Activation functions
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for generating a classifier, comprising: initializing a neural network with a fully connected architecture; applying a regularization constraint to the set of weights between neurons in the input layer and the plurality of latent features in the hidden layer; iteratively reducing a number of incoming connections to each latent feature in the hidden layer to a predetermined number based on the regularized first set of weights; weighting loss function's value based on categories of activation tuples, wherein contributions of data entries with activation tuples of size greater than a predetermined threshold to the loss function's value are limited and wherein contributions of data entries with activation tuples of size “0” to the loss function's value are minimized, to a predefined percentage; and selectively updating sets of weights associated with top-ranked latent features as evaluated by the magnitude of their contributions at the output layer in a training process.

## Claims

### Claim 1

A computer-implemented method for generating a classifier, comprising:
initializing a neural network classifier with a fully connected architecture comprising an input layer, a hidden layer, and an output layer, wherein the hidden layer comprises a plurality of latent features;
applying a regularization constraint to a first set of weights between neurons in the input layer and the plurality of latent features in the hidden layer;
iteratively reducing a number of incoming connections to each latent feature in the hidden layer to a predetermined number per latent feature based on the regularized first set of weights;
upon a determination that a proportion of data entries with activation tuples of size “0” is below a specified threshold, employing a loss function weighting based on activation tuples, wherein contributions of data entries with activation tuples of size greater than a predetermined threshold are minimized and wherein contributions of data entries with activation tuples of size “0” are reduced to a predefined percentage; and
selectively updating a second set of weights of top-ranked latent features as evaluated by a magnitude of their contributions at the output layer in a training process.

### Claim 2 (depends on 1)

The method of claim 1, wherein the predetermined number of incoming connections to each latent feature is one or two.

### Claim 3 (depends on 1)

The method of claim 1, wherein the regularization constraint applied to the first set of weights is an L1-based regularization constraint.

### Claim 4 (depends on 1)

The method of claim 1, wherein the specified threshold for the proportion of data entries with activation tuples of size “0” is less than or equal to a predetermined percentage.

### Claim 5 (depends on 1)

The method of claim 1, further comprising adjusting a learning rate during different stages of the training process.

### Claim 6 (depends on 1)

The method of claim 1, wherein the iteratively reducing the number of incoming connections to each latent feature in the hidden layer comprises evaluating an importance of each connection based on a magnitude of the regularized first set of weights.

### Claim 7 (depends on 6)

The method of claim 6, wherein the iteratively reducing the number of incoming connections further comprises retaining only top-ranked connections for each latent feature, constraining the remaining connections to zero.

### Claim 8

A computer program product comprising a non-transient machine-readable medium storing instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:
initializing a neural network classifier with a fully connected architecture comprising an input layer, a hidden layer, and an output layer, wherein the hidden layer comprises a plurality of latent features;
applying a regularization constraint to a first set of weights between neurons in the input layer and the plurality of latent features in the hidden layer;
iteratively reducing a number of incoming connections to each latent feature in the hidden layer to a predetermined number per latent feature based on the regularized first set of weights;
upon a determination that a proportion of data entries with activation tuples of size “0” is below a specified threshold, employing a loss function weighting based on activation tuples, wherein contributions of data entries with activation tuples of size greater than a predetermined threshold are minimized and wherein contributions of data entries with activation tuples of size “0” are reduced to a predefined percentage; and
selectively updating a second set of weights of top-ranked latent features as evaluated by a magnitude of their contributions at the output layer in a training process.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the predetermined number of incoming connections to each latent feature is one or two.

### Claim 10 (depends on 8)

The computer program product of claim 8, wherein the regularization constraint applied to the first set of weights is an L1-based regularization constraint.

### Claim 11 (depends on 8)

The computer program product of claim 8, wherein the specified threshold for the proportion of data entries with activation tuples of size “0” is less than or equal to a predetermined percentage.

### Claim 12 (depends on 8)

The computer program product of claim 8, further comprising adjusting a learning rate during different stages of the training process.

### Claim 13 (depends on 8)

The computer program product of claim 8, wherein the iteratively reducing the number of incoming connections to each latent feature in the hidden layer comprises evaluating an importance of each connection based on a magnitude of the regularized first set of weights.

### Claim 14 (depends on 13)

The computer program product of claim 13, wherein the iteratively reducing the number of incoming connections further comprises retaining only top-ranked connections for each latent feature, constraining the remaining connections to zero.

### Claim 15

A system comprising:
at least one programmable processor; and
a non-transient machine-readable medium storing instructions that, when executed by the processor, cause the at least one programmable processor to perform operations comprising:
initializing a neural network classifier with a fully connected architecture comprising an input layer, a hidden layer, and an output layer, wherein the hidden layer comprises a plurality of latent features;
applying a regularization constraint to a first set of weights between neurons in the input layer and the plurality of latent features in the hidden layer;
iteratively reducing a number of incoming connections to each latent feature in the hidden layer to a predetermined number per latent feature based on the regularized first set of weights;
upon a determination that a proportion of data entries with activation tuples of size “0” is below a specified threshold, employing a loss function weighting based on activation tuples, wherein contributions of data entries with activation tuples of size greater than a predetermined threshold are minimized and wherein contributions of data entries with activation tuples of size “0” are reduced to a predefined percentage; and
selectively updating a second set of weights of top-ranked latent features as evaluated by a magnitude of their contributions at the output layer in a training process.

### Claim 16 (depends on 15)

The system of claim 15, wherein the predetermined number of incoming connections to each latent feature is one or two.

### Claim 17 (depends on 15)

The system of claim 15, wherein the regularization constraint applied to the first set of weights is an Li-based regularization constraint.

### Claim 18 (depends on 15)

The system of claim 15, wherein the specified threshold for the proportion of data entries with activation tuples of size “0” is less than or equal to a predetermined percentage.

### Claim 19 (depends on 15)

The system of claim 15, further comprising adjusting a learning rate during different stages of the training process.

### Claim 20 (depends on 15)

The system of claim 15, wherein the iteratively reducing the number of incoming connections to each latent feature in the hidden layer comprises evaluating an importance of each connection based on a magnitude of the regularized first set of weights.
