A Novel Progressive Learning Technique for Multi-class Classification
This addresses the problem of incremental learning in real-world applications for AI systems that need to adapt to new classes over time, though it appears incremental as it builds on existing progressive learning concepts.
The paper tackles the problem of multi-class classification when the number of classes is unknown and online learning is required, proposing a progressive learning technique that automatically remodels neural networks to add new classes while retaining previous knowledge. The technique is evaluated on standard datasets and shown to be superior in a comparative study.
In this paper, a progressive learning technique for multi-class classification is proposed. This newly developed learning technique is independent of the number of class constraints and it can learn new classes while still retaining the knowledge of previous classes. Whenever a new class (non-native to the knowledge learnt thus far) is encountered, the neural network structure gets remodeled automatically by facilitating new neurons and interconnections, and the parameters are calculated in such a way that it retains the knowledge learnt thus far. This technique is suitable for real-world applications where the number of classes is often unknown and online learning from real-time data is required. The consistency and the complexity of the progressive learning technique are analyzed. Several standard datasets are used to evaluate the performance of the developed technique. A comparative study shows that the developed technique is superior.