Sparse Neural Network Topology for Faster Convergence

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing neural networks for modeling complex physical systems are redundant, leading to slow learning processes, high data requirements, and poor convergence, making them unsuitable for real-time simulation and dynamic modeling, especially when data is limited.

Innovation Solution

A method for constructing a sparse neural network with rapid Gauss-Newton type convergence, involving topological optimization through additive and subtractive phases, to adapt the network structure to the specific task, using a Lagrange operator for efficient error estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If redundant neural networks with many connections are used, then learning process is more robust against local minima, but learning speed decreases and data requirements increase

Engineering Contradiction:
Improvelearning robustnessVSAvoidlearning speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent extracts and removes redundant connections from the neural network, keeping only the essential connections needed for learning. This is achieved through a sparse network architecture that identifies and eliminates unnecessary weights, thereby reducing complexity while maintaining learning robustness.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different connection densities to different parts of the network. Instead of uniform redundancy throughout, the network has localized dense regions where connections are critical and sparse regions where connections can be eliminated, optimizing both robustness and efficiency.

Inventive Principle:
Principle #3Local quality

2Reliability

If neural network size is increased to avoid local minima, then learning reliability improves, but convergence rate decreases

Engineering Contradiction:
Improvelearning reliabilityVSAvoidconvergence time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts the essential functional connections needed for reliable learning while removing extraneous connections that increase convergence time. The sparse architecture identifies minimal sufficient connectivity, achieving reliability without the time penalty of large redundant networks.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent employs dynamic connection pruning during the learning process, where connections are added or removed based on their contribution to learning. This dynamic adaptation allows the network to maintain reliability while optimizing convergence speed at each training stage.

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If manual trial-and-error topology construction is used, then network adaptability to specific tasks improves, but device complexity and construction time increase

Engineering Contradiction:
Improvetask-specific adaptabilityVSAvoidnetwork construction complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent enables the neural network to automatically determine its own optimal topology through self-organizing mechanisms. The network structure emerges from the data and task requirements without manual intervention, achieving task-specific adaptability while eliminating the complexity of manual design.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent pre-defines a sparse topology framework that guides subsequent learning. This preliminary structural guidance accelerates convergence and reduces the search space, allowing the network to adapt to specific tasks efficiently without exhaustive manual trial-and-error.

Inventive Principle:
Principle #10Preliminary action

4Measurement precision

If massive amounts of data are used for training redundant networks, then learning accuracy improves, but data storage and processing requirements increase

Engineering Contradiction:
Improvelearning accuracyVSAvoiddata volume
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts the essential patterns from smaller datasets by using a sparse network architecture that focuses learning capacity on critical features. This reduces the need for massive data volumes while maintaining learning accuracy through efficient parameter utilization.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the parameter configuration from dense to sparse connectivity, fundamentally altering how the network processes information. This parameter change enables effective learning with reduced data volumes by concentrating computational resources on the most informative parameters and connections.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3877912B1Method of neural network construction
Publication Date: 2026.04.01 ADAGOS
  • EP3877912B1 patent drawingFigure 1~2
  • EP3877912B1 patent drawingFigure 3
  • EP3877912B1 patent drawingFigure 4C~4b

AI summary

The subject of the invention is a method for constructing a forward propagation neural network, a set of nodes and of connection between the nodes forming a topology organized into layers, such that each layer is defined by a set of computable nodes that can be calculated during one and the same step, and the input of a processing node of a layer can be connected to the output of a node of any one of the previous layers, the method comprising a step of initializing a neural network according to an initial topology and at least one topological optimization phase, of which each phase comprises: - at least one additive phase comprising the modification of the topology of the network by the addition of at least one node and/or a connection link between the input of a node of a layer and the output of a node of any one of the previous layers, and/or - at least one subtractive phase comprising the modification of the topology of the network by the deletion of at least one node and/or a connection link between two layers, and in which each topology modification comprises the selecting of a topology modification from among a plurality of candidate modifications, on the basis of an estimation of the variation of the error of the network between each topology modified according to a candidate modification and the previous topology.