Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learning [0.03%]
层次聚类优化了任务结构的组合性和表达性之间的权衡，以实现灵活的强化学习
Rex G Liu,Michael J Frank
Rex G Liu
A hallmark of human intelligence, but challenging for reinforcement learning (RL) agents, is the ability to compositionally generalise, that is, to recompose familiar knowledge components in novel ways to solve new problems. For instance, w...
David Kartchner,Davi Nakajima An,Wendi Ren et al.
David Kartchner et al.
A major bottleneck preventing the extension of deep learning systems to new domains is the prohibitive cost of acquiring sufficient training labels. Alternatives such as weak supervision, active learning, and fine-tuning of pretrained model...
Learning in the Machine: Random Backpropagation and the Deep Learning Channel [0.03%]
机器中的学习：随机反向传播和深度学习信道
Pierre Baldi,Peter Sadowski,Zhiqin Lu
Pierre Baldi
Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is remar...
Methods for solving reasoning problems in abstract argumentation - A survey [0.03%]
抽象论证中的推理问题解法研究综述
Günther Charwat,Wolfgang Dvořák,Sarah A Gaggl et al.
Günther Charwat et al.
Within the last decade, abstract argumentation has emerged as a central field in Artificial Intelligence. Besides providing a core formalism for many advanced argumentation systems, abstract argumentation has also served to capture several ...
Modeling the Complex Dynamics and Changing Correlations of Epileptic Events [0.03%]
建模癫痫发作的复杂动力学和变化的相关性
Drausin F Wulsin,Emily B Fox,Brian Litt
Drausin F Wulsin
Patients with epilepsy can manifest short, sub-clinical epileptic "bursts" in addition to full-blown clinical seizures. We believe the relationship between these two classes of events-something not previously studied quantitatively-could yi...
Pierre Baldi,Peter Sadowski
Pierre Baldi
Dropout is a recently introduced algorithm for training neural network by randomly dropping units during training to prevent their co-adaptation. A mathematical analysis of some of the static and dynamic properties of dropout is provided us...
Using Wikipedia to learn semantic feature representations of concrete concepts in neuroimaging experiments [0.03%]
利用Wikipedia从神经影像实验中学习具体概念的语义特征表示方法
Francisco Pereira,Matthew Botvinick,Greg Detre
Francisco Pereira
In this paper we show that a corpus of a few thousand Wikipedia articles about concrete or visualizable concepts can be used to produce a low-dimensional semantic feature representation of those concepts. The purpose of such a representatio...
Michael McGeachie,Jon Doyle
Michael McGeachie
Existing representations for multiattribute ceteris paribus preference statements have provided useful treatments and clear semantics for qualitative comparisons, but have not provided similarly clear representations or semantics for compar...
Thomas Eiter,Esra Erdem,Michael Fink et al.
Thomas Eiter et al.
Incorporating new information into a knowledge base is an important problem which has been widely investigated. In this paper, we study this problem in a formal framework for reasoning about actions and change. In this framework, action dom...
A comparative runtime analysis of heuristic algorithms for satisfiability problems [0.03%]
启发式算法在可满足性问题上的运行时间分析比较研究
Yuren Zhou,Jun He,Qing Nie
Yuren Zhou
The satisfiability problem is a basic core NP-complete problem. In recent years, a lot of heuristic algorithms have been developed to solve this problem, and many experiments have evaluated and compared the performance of different heuristi...