mlsanityData to 14 Oct 2026

Neurogenesis Deep Learning

arXiv 1612.03770 ↗First posted 12 Dec 2016cs.NE cs.LG stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing - data processing domains in which humans have long held clear advantages over conventional algorithms. In contrast to biological neural systems, which are capable of learning continuously, deep artificial networks have a limited ability for incorporating new information in an already trained network. As a result, methods for continuous learning are potentially highly impactful in enabling the application of deep networks to dynamic data sets. Here, inspired by the process of adult neurogenesis in the hippocampus, we explore the potential for adding new neurons to deep layers of artificial neural networks in order to facilitate their acquisition of novel information while preserving previously trained data representations. Our results on the MNIST handwritten digit dataset and the NIST SD 19 dataset, which includes lower and upper case letters and digits, demonstrate that neurogenesis is well suited for addressing the stability-plasticity dilemma that has long challenged adaptive machine learning algorithms.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 10; 2023: 5; 2024: 3; 2025: 3.

32 papers.

Sort:

  1. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 177
  2. 2021DEMix Layers: Disentangling Domains for Modular Language Modelingcited by 132
  3. 2024Continual Learning and Catastrophic Forgettingcited by 77
  4. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 72
  5. 2021Learngene: From Open-World to Your Learning Taskcited by 27
  6. 2023SIESTA: Efficient Online Continual Learning with Sleepcited by 24
  7. 2022Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activationcited by 16
  8. 2023Self-Expanding Neural Networkscited by 14
  9. 2024Optimal Protocols for Continual Learning via Statistical Physics and Control Theorycited by 14
  10. 2023Overcoming the Stability Gap in Continual Learningcited by 13
  11. 2022Self-Activating Neural Ensembles for Continual Reinforcement Learningcited by 7
  12. 2021FFNB: Forgetting-Free Neural Blocks for Deep Continual Visual Learningcited by 6
20 more
  1. 2021Towards continual task learning in artificial neural networks: current approaches and insights from neurosciencecited by 6
  2. 2022Addressing Client Drift in Federated Continual Learning with Adaptive Optimizationcited by 5
  3. 2021Incremental Deep Neural Network Learning using Classification Confidence Thresholdingcited by 3
  4. 2022Augmentative Topology Agents For Open-Ended Learningcited by 3
  5. 2022Cold Start Streaming Learning for Deep Networkscited by 3
  6. 2021Towards Heterogeneous Clients with Elastic Federated Learningcited by 2
  7. 2022Lifelong Learning for Neural powered Mixed Integer Programmingcited by 2
  8. 2021Incremental Class Learning using Variational Autoencoders with Similarity Learningcited by 1
  9. 2021Accretionary Learning with Deep Neural Networkscited by 1
  10. 2021Reviewing continual learning from the perspective of human-level intelligencecited by 1
  11. 2021Object Pursuit: Building a Space of Objects via Discriminative Weight Generationcited by 1
  12. 2022Learning Citywide Patterns of Life from Trajectory Monitoringcited by 1
  13. 2022Continual Few-Shot Learning with Adversarial Class Storagecited by 1
  14. 2022Review learning: Real world validation of privacy preserving continual learning across medical institutionscited by 1
  15. 2023Towards Robust Continual Learning with Bayesian Adaptive Moment Regularizationcited by 1
  16. 2025Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticitycited by 1
  17. 2022CULT: Continual Unsupervised Learning with Typicality-Based Environment Detectioncited by 0
  18. 2024Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Datacited by 0
  19. 2025Continual learning via probabilistic exchangeable sequence modellingcited by 0
  20. 2025Investigation of D-Wave quantum annealing for training Restricted Boltzmann Machines and mitigating catastrophic forgettingcited by 0