Share This Author
Exploration by Random Network Distillation
An exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed and a method to flexibly combine intrinsic and extrinsic rewards that enables significant progress on several hard exploration Atari games is introduced.
Large-Scale Study of Curiosity-Driven Learning
- Yuri Burda, Harrison Edwards, Deepak Pathak, A. Storkey, Trevor Darrell, Alexei A. Efros
- Computer ScienceICLR
- 13 August 2018
This paper performs the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite, and shows surprisingly good performance.
CINIC-10 is not ImageNet or CIFAR-10
This brief technical report introduces the CINIC-10 dataset as a plug-in extended alternative for CIFAR-10, and presents the approach to compiling the dataset, illustrating the example images for different classes, and giving pixel distributions for each part of the repository.
How to train your MAML
This paper proposes various modifications to MAML that not only stabilize the system, but also substantially improve the generalization performance, convergence speed and computational overhead of MAMl, which it is called M AML++.
Three Factors Influencing Minima in SGD
Through this analysis, it is found that three factors – learning rate, batch size and the variance of the loss gradients – control the trade-off between the depth and width of the minima found by SGD, with wider minima favoured by a higher ratio of learning rate to batch size.
Data Augmentation Generative Adversarial Networks
It is shown that a Data Augmentation Generative Adversarial Network (DAGAN) augments standard vanilla classifiers well and can enhance few-shot learning systems such as Matching Networks.
Censoring Representations with an Adversary
This work forms the adversarial model as a minimax problem, and optimize that minimax objective using a stochastic gradient alternate min-max optimizer, and demonstrates the ability to provide discriminant free representations for standard test problems, and compares with previous state of the art methods for fairness.
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 16
- A. Storkey
- Computer ScienceNIPS
Towards a Neural Statistician
An extension of a variational autoencoder that can learn a method for computing representations, or statistics, of datasets in an unsupervised fashion is demonstrated that is able to learn statistics that can be used for clustering datasets, transferring generative models to new datasets, selecting representative samples of datasets and classifying previously unseen classes.
Meta-Learning in Neural Networks: A Survey
- Timothy M. Hospedales, Antreas Antoniou, P. Micaelli, A. Storkey
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 11 April 2020
A new taxonomy is proposed that provides a more comprehensive breakdown of the space of meta-learning methods today and surveys promising applications and successes ofMeta-learning such as few-shot learning and reinforcement learning.