Neural Network Feature Compression for Reliable Inference

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for machine learning inference processing face reliability issues due to varying data sizes and compression methods that can prevent consistent inference, particularly in cases where data size after compression is undefined, leading to unpredictable inference success.

Innovation Solution

An information processing apparatus and method that includes a preliminary analysis unit to generate control information for controlling compression and decoding of feature amounts, using a compression unit to compress and a decoding unit to decode feature amounts based on this control information, ensuring reliable inference processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If dynamic compression rate is used to reduce data size, then memory usage and data communication amount are reduced, but inference reliability deteriorates because data size after compression cannot be defined

Engineering Contradiction:
Improvedata sizeVSAvoidinference reliability
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The system performs preliminary analysis of the neural network structure and data characteristics before compression to determine appropriate compression parameters. This advance preparation ensures that compression settings are optimized for the specific inference task, guaranteeing that compressed data will maintain sufficient quality for reliable inference while achieving the desired size reduction.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts compression parameters based on analysis results rather than using fixed or purely data-driven compression rates. By changing compression parameters (such as quantization precision, block size, or encoding settings) based on neural network architecture and data statistics, the system achieves both size reduction and inference reliability.

Inventive Principle:
Principle #35Parameter changes

2Volume of stationary object

If compression is applied to reduce data size, then memory capacity requirements are reduced, but data processing reliability deteriorates due to undefined compressed data size

Engineering Contradiction:
Improvememory capacityVSAvoidprocessing reliability
Core Design Contradiction:
Volume of stationary objectVSReliability

Solution Approach 1:

The system performs preliminary analysis of the neural network structure and data characteristics before compression to determine appropriate compression parameters. This advance preparation ensures that compression settings are optimized for the specific inference task, guaranteeing that compressed data will maintain sufficient quality for reliable inference while achieving the desired size reduction.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system incorporates feedback mechanisms where compression parameters are adjusted based on the actual performance of inference processing. By monitoring whether compressed data maintains sufficient quality for accurate inference and using this feedback to refine future compression settings, the system ensures both memory efficiency and processing reliability.

Inventive Principle:
Principle #23Feedback

3Quantity of substance

If dynamic compression is used, then data size is reduced, but the complexity of controlling compression and decoding increases

Engineering Contradiction:
Improvedata sizeVSAvoidcompression control complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The system performs preliminary analysis of the neural network structure and data characteristics before compression to determine appropriate compression parameters. This advance preparation ensures that compression settings are optimized for the specific inference task, guaranteeing that compressed data will maintain sufficient quality for reliable inference while achieving the desired size reduction.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4645862A1Information processing apparatus and information processing method
Publication Date: 2025.11.05 SONY SEMICON SOLUTIONS CORP
  • EP4645862A1 patent drawingFigure 1~2
  • EP4645862A1 patent drawingFigure 3
  • EP4645862A1 patent drawingFigure 4A~4B

AI summary

The present disclosure relates to an information processing apparatus and an information processing method that enable inference of machine learning to be performed more reliably. Provided is an information processing apparatus including: a preliminary analysis unit that analyzes a neural network before inference using the neural network is performed and generates control information for controlling compression and decoding of a feature amount processed by the neural network; a computing unit that performs inference using input data and the neural network and outputs a processing result obtained by processing the feature amount obtained from the input data as a computing result; a compression unit that compresses the feature amount input from the computing unit on the basis of the control information and records a compressed feature amount that is the feature amount having been compressed in a memory; and a decoding unit that decodes the compressed feature amount temporarily recorded in the memory on the basis of the control information and outputs the decoded feature amount to the computing unit. The present disclosure can be applied to, for example, a machine learning inference unit.