Designing neural networks through neuroevolution
Much of recent machine learning has focused on deep learning, in which neural network
weights are trained through variants of stochastic gradient descent. An alternative approach …
weights are trained through variants of stochastic gradient descent. An alternative approach …
Artificial neural networks for neuroscientists: a primer
Artificial neural networks (ANNs) are essential tools in machine learning that have drawn
increasing attention in neuroscience. Besides offering powerful techniques for data analysis …
increasing attention in neuroscience. Besides offering powerful techniques for data analysis …
Meta-learning in neural networks: A survey
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
A survey of deep meta-learning
M Huisman, JN Van Rijn, A Plaat - Artificial Intelligence Review, 2021 - Springer
Deep neural networks can achieve great successes when presented with large data sets
and sufficient computational resources. However, their ability to learn new concepts quickly …
and sufficient computational resources. However, their ability to learn new concepts quickly …
Frozen pretrained transformers as universal computation engines
We investigate the capability of a transformer pretrained on natural language to generalize
to other modalities with minimal finetuning--in particular, without finetuning of the self …
to other modalities with minimal finetuning--in particular, without finetuning of the self …
A survey of meta-reinforcement learning
While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …
machine learning, it is held back from more widespread adoption by its often poor data …
Random feature attention
Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their
core is an attention function which models pairwise interactions between the inputs at every …
core is an attention function which models pairwise interactions between the inputs at every …
Linear transformers are secretly fast weight programmers
We show the formal equivalence of linearised self-attention mechanisms and fast weight
controllers from the early'90s, where a slow neural net learns by gradient descent to …
controllers from the early'90s, where a slow neural net learns by gradient descent to …
Stabilizing transformers for reinforcement learning
Owing to their ability to both effectively integrate information over long time horizons and
scale to massive amounts of data, self-attention architectures have recently shown …
scale to massive amounts of data, self-attention architectures have recently shown …
Meta-learning with warped gradient descent
Learning an efficient update rule from data that promotes rapid learning of new tasks from
the same distribution remains an open problem in meta-learning. Typically, previous works …
the same distribution remains an open problem in meta-learning. Typically, previous works …