Continual learning under domain transfer with sparse synaptic bursting

• URL: http://arxiv.org/abs/2108.12056v9
• Date: Tue, 16 Jan 2024 18:55:17 GMT
• Title: Continual learning under domain transfer with sparse synaptic bursting
• Authors: Shawn L. Beaulieu, Jeff Clune, Nick Cheney
• Abstract summary: We introduce a system that can learn sequentially over previously unseen datasets with little forgetting over time. We find that our method learns continually under domain transfer with sparse bursts of activity in weights that are recycled across tasks.
• Score: 2.314558204145174
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Existing machines are functionally specific tools that were made for easy prediction and control. Tomorrow's machines may be closer to biological systems in their mutability, resilience, and autonomy. But first they must be capable of learning and retaining new information without being exposed to it arbitrarily often. Past efforts to engineer such systems have sought to build or regulate artificial neural networks using disjoint sets of weights that are uniquely sensitive to specific tasks or inputs. This has not yet enabled continual learning over long sequences of previously unseen data without corrupting existing knowledge: a problem known as catastrophic forgetting. In this paper, we introduce a system that can learn sequentially over previously unseen datasets (ImageNet, CIFAR-100) with little forgetting over time. This is done by controlling the activity of weights in a convolutional neural network on the basis of inputs using top-down regulation generated by a second feed-forward neural network. We find that our method learns continually under domain transfer with sparse bursts of activity in weights that are recycled across tasks, rather than by maintaining task-specific modules. Sparse synaptic bursting is found to balance activity and suppression such that new functions can be learned without corrupting extant knowledge, thus mirroring the balance of order and disorder in systems at the edge of chaos. This behavior emerges during a prior pre-training (or 'meta-learning') phase in which regulated synapses are selectively disinhibited, or grown, from an initial state of uniform suppression through prediction error minimization.

Related papers

• ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks [1.5931140598271163]
  We build a model for efficient learning sequences using only local always-on and phase-free plasticity. We showcase the capabilities of ELiSe in a mock-up of birdsong learning, and demonstrate its flexibility with respect to parametrization.
  arXiv  Detail & Related papers  (2024-02-26T17:30:34Z)
• Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps [56.827895559823126]
  Self-organizing map (SOM) is a neural model often used in clustering and dimensionality reduction. We propose a generalization of the SOM, the continual SOM, which is capable of online unsupervised learning under a low memory budget. Our results, on benchmarks including MNIST, Kuzushiji-MNIST, and Fashion-MNIST, show almost a two times increase in accuracy.
  arXiv  Detail & Related papers  (2024-02-19T19:11:22Z)
• IF2Net: Innately Forgetting-Free Networks for Continual Learning [49.57495829364827]
  Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, we investigated how to design an Innately Forgetting-Free Network (IF2Net) IF2Net allows a single network to inherently learn unlimited mapping rules without telling task identities at test time.
  arXiv  Detail & Related papers  (2023-06-18T05:26:49Z)
• Artificial Neuronal Ensembles with Learned Context Dependent Gating [0.0]
  We introduce Learned Context Dependent Gating (LXDG), a method to flexibly allocate and recall artificial neuronal ensembles' Activities in the hidden layers of the network are modulated by gates, which are dynamically produced during training. We demonstrate the ability of this method to alleviate catastrophic forgetting on continual learning benchmarks.
  arXiv  Detail & Related papers  (2023-01-17T20:52:48Z)
• The least-control principle for learning at equilibrium [65.2998274413952]
  We present a new principle for learning equilibrium recurrent neural networks, deep equilibrium models, or meta-learning. Our results shed light on how the brain might learn and offer new ways of approaching a broad class of machine learning problems.
  arXiv  Detail & Related papers  (2022-07-04T11:27:08Z)
• Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning [1.9580473532948401]
  We introduce a novel neural network architecture inspired by neuromodulation in biological nervous systems. We show that this approach has strong learning performance per task despite the very small number of learnable parameters.
  arXiv  Detail & Related papers  (2022-04-08T21:12:13Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay [67.50637511633212]
  A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day.
  arXiv  Detail & Related papers  (2021-12-09T07:11:14Z)
• Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent [62.997667081978825]
  We use neural cellular automata to control a cart-pole agent. We trained the model using deep-Q learning, where the states of the output cells were used as the Q-value estimates to be optimized.
  arXiv  Detail & Related papers  (2021-06-29T10:49:42Z)
• Learning to Continually Learn [14.988129334830003]
  We propose A Neuromodulated Meta-Learning Algorithm (ANML) Inspired by neuromodulatory processes in the brain, we propose A Neuromodulated Meta-Learning Algorithm (ANML) ANML produces state-of-the-art continual learning performance, sequentially learning as many as 600 classes (over 9,000 SGD updates)
  arXiv  Detail & Related papers  (2020-02-21T22:52:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.