Meta-Learning through Hebbian Plasticity in Random Networks

Najarro, Elias; Risi, Sebastian

doi:10.48550/arxiv.2007.02686

Cited by 9 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synaptic plasticity is a powerful mechanism for unsupervised learning in neural networks, inspired by learning processes in the biological brain [1,2,3,4,5]. This process has been incorporated into spiking and artificial neural networks to enable intra-lifetime learning [8,9,10,11,12,13]. However, in this work it was shown that plastic ANNs struggle to generalize their behavior beyond the training time horizon.…”

Section: Discussionmentioning

confidence: 96%

“…In the field of Artificial Intelligence (AI), the primary focus of research with ANNs has been on discovering static solutions, where the synaptic weights remain constant throughout the lifetime of the organism. Inspired by the biological brain, a rich history of work has demonstrated the design of ANNs together with synaptic plasticity [8,9,10,11,12,13], referred to as Plastic Artificial Neural Networks (PANNs). These networks have shown impressive capabilities in their ability to generalize to novel environmental circumstances, recover from limb damage, enhance memory [11,14,5].…”

Section: Introductionmentioning

confidence: 99%

“…Inspired by the biological brain, a rich history of work has demonstrated the design of ANNs together with synaptic plasticity [8,9,10,11,12,13], referred to as Plastic Artificial Neural Networks (PANNs). These networks have shown impressive capabilities in their ability to generalize to novel environmental circumstances, recover from limb damage, enhance memory [11,14,5]. However, the methods used in these works are trained and operated across finite time horizons.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks

Schmidgall¹,

Hays²

2021

Preprint

View full text Add to dashboard Cite

Synaptic plasticity poses itself as a powerful method of self-regulated unsupervised learning in neural networks. A recent resurgence of interest has developed in utilizing Artificial Neural Networks (ANNs) together with synaptic plasticity for intra-lifetime learning. Plasticity has been shown to improve the learning capabilities of these networks in generalizing to novel environmental circumstances. However, the long-term stability of these trained networks has yet to be examined. This work demonstrates that utilizing plasticity together with ANNs leads to instability beyond the prespecified lifespan used during training. This instability can lead to the dramatic decline of reward seeking behavior, or quickly lead to reaching environment terminal states. This behavior is shown to hold consistent for several plasticity rules on two different environments across many training time-horizons: a cart-pole balancing problem and a quadrupedal locomotion problem. We present a solution to this instability through the use of spiking neurons.

show abstract

Section: Discussionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks

Schmidgall¹,

Hays²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Modern deep learning systems are generally unable to adapt to a sudden reordering of sensory inputs, unless the model is retrained, or if the user manually corrects the ordering of the inputs for the model. However, techniques from continual meta-learning, such as adaptive weights [2,35,64], Hebbian-learning [51,52,56], and model-based [1,19,36,37] approaches can help the model adapt to such changes, and remain a promising active area of research.…”

Section: Introductionmentioning

confidence: 99%

The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning

Tang¹,

Ha²

2021

Preprint

View full text Add to dashboard Cite

In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the full picture. Such systems have inspired development of artificial intelligence algorithms in areas such as swarm optimization and cellular automata. Motivated by the emergence of collective behavior from complex cellular systems, we build systems that feed each sensory input from the environment into distinct, but identical neural networks, each with no fixed relationship with one another. We show that these sensory networks can be trained to integrate information received locally, and through communication via an attention mechanism, can collectively produce a globally coherent policy. Moreover, the system can still perform its task even if the ordering of its inputs is randomly permuted several times during an episode. These permutation invariant systems also display useful robustness and generalization properties that are broadly applicable. Interactive demo and videos of our results: https://attentionneuron.github.io/

show abstract

“…procedures operating over local data. As an example of the latter, it is possible to meta-learn local iterative rules [9], [10], initializations [11]- [13], or learning rates [14].…”

Section: Introductionmentioning

confidence: 99%

Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning

Rosenfeld¹,

Rajendran²,

Simeone³

2021

Preprint

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs) have recently gained popularity as machine learning models for on-device edge intelligence for applications such as mobile healthcare management and natural language processing due to their low power profile. In such highly personalized use cases, it is important for the model to be able to adapt to the unique features of an individual with only a minimal amount of training data. Meta-learning has been proposed as a way to train models that are geared towards quick adaptation to new tasks. The few existing meta-learning solutions for SNNs operate offline and require some form of backpropagation that is incompatible with the current neuromorphic edge-devices. In this paper, we propose an online-within-online meta-learning rule for SNNs termed OWOML-SNN, that enables lifelong learning on a stream of tasks, and relies on local, backprop-free, nested updates.

show abstract

Meta-Learning through Hebbian Plasticity in Random Networks

Cited by 9 publications

References 0 publications

Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks

Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks

The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning

Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning

Contact Info

Product

Resources

About