Differentiable plasticity: training plastic neural networks with backpropagation
How can we build agents that keep learning from experience, quickly and efficiently, after
their initial training? Here we take inspiration from the main mechanism of learning in …
their initial training? Here we take inspiration from the main mechanism of learning in …
Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
The impressive lifelong learning in animal brains is primarily enabled by plastic changes in
synaptic connectivity. Importantly, these changes are not passive, but are actively controlled …
synaptic connectivity. Importantly, these changes are not passive, but are actively controlled …
Meta-learning through hebbian plasticity in random networks
Lifelong learning and adaptability are two defining aspects of biological agents. Modern
reinforcement learning (RL) approaches have shown significant progress in solving complex …
reinforcement learning (RL) approaches have shown significant progress in solving complex …
Disentangling the causes of plasticity loss in neural networks
Underpinning the past decades of work on the design, initialization, and optimization of
neural networks is a seemingly innocuous assumption: that the network is trained on a\textit …
neural networks is a seemingly innocuous assumption: that the network is trained on a\textit …
[HTML][HTML] Neural modularity helps organisms evolve to learn new skills without forgetting old skills
A long-standing goal in artificial intelligence is creating agents that can learn a variety of
different skills for different problems. In the artificial intelligence subfield of neural networks …
different skills for different problems. In the artificial intelligence subfield of neural networks …
Evolving plastic neural networks with novelty search
Biological brains can adapt and learn from past experience. Yet neuroevolution, that is,
automatically creating artificial neural networks (ANNs) through evolutionary algorithms, has …
automatically creating artificial neural networks (ANNs) through evolutionary algorithms, has …
[HTML][HTML] Neuromorphic hardware learns to learn
Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by
hand to suit a particular task. In contrast, networks of neurons in the brain were optimized …
hand to suit a particular task. In contrast, networks of neurons in the brain were optimized …
[HTML][HTML] Mirrored STDP implements autoencoder learning in a network of spiking neurons
KS Burbank - PLoS computational biology, 2015 - journals.plos.org
The autoencoder algorithm is a simple but powerful unsupervised method for training neural
networks. Autoencoder networks can learn sparse distributed codes similar to those seen in …
networks. Autoencoder networks can learn sparse distributed codes similar to those seen in …
Evolutionary advantages of neuromodulated plasticity in dynamic, reward-based scenarios
A Soltoggio, JA Bullinaria, C Mattiussi… - Proceedings of the …, 2008 - infoscience.epfl.ch
Abstract memory in biological neural networks. Similarly, artificial neural networks could
benefit from modulatory dynamics when facing certain types of learning problem. Here we …
benefit from modulatory dynamics when facing certain types of learning problem. Here we …
Evolving large-scale neural networks for vision-based reinforcement learning
The idea of using evolutionary computation to train artificial neural networks, or
neuroevolution (NE), for reinforcement learning (RL) tasks has now been around for over 20 …
neuroevolution (NE), for reinforcement learning (RL) tasks has now been around for over 20 …