Continual Learning for Pattern Recognizers using Neurogenesis Deep Learning
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Deep neural networks have emerged as a leading set of algorithms to infer information from a variety of data sources such as images and time series data. In their most basic form, neural networks lack the ability to adapt to new classes of information. Continual learning is a field of study attempting to give previously trained deep learning models the ability to adapt to a changing environment. Previous work developed a CL method called Neurogenesis for Deep Learning (NDL). Here, we combine NDL with a specific neural network architecture (the Ladder Network) to produce a system capable of automatically adapting a classification neural network to new classes of data. The NDL Ladder Network was evaluated against other leading CL methods. While the NDL and Ladder Network system did not match the cutting edge performance achieved by other CL methods, in most cases it performed comparably and is the only system evaluated that can learn new classes of information with no human intervention.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 1855019
- Report Number(s):
- SAND2021-11382R; 700603
- Country of Publication:
- United States
- Language:
- English
Similar Records
Using High Performance Computing to Examine the Processes of Neurogenesis Underlying Pattern Separation/Completion of Episodic Information.
Deeply learning deep inelastic scattering kinematics