Deep learning in neural networks: An overview
J Schmidhuber - Neural networks, 2015 - Elsevier
In recent years, deep artificial neural networks (including recurrent ones) have won
numerous contests in pattern recognition and machine learning. This historical survey …
numerous contests in pattern recognition and machine learning. This historical survey …
Exploration, novelty, surprise, and free energy minimization
P Schwartenbeck, T FitzGerald, RJ Dolan… - Frontiers in …, 2013 - frontiersin.org
This paper reviews recent developments under the free energy principle that introduce a
normative perspective on classical economic (utilitarian) decision-making based on (active) …
normative perspective on classical economic (utilitarian) decision-making based on (active) …
Computational mechanisms of curiosity and goal-directed exploration
Successful behaviour depends on the right balance between maximising reward and
soliciting information about the world. Here, we show how different types of information-gain …
soliciting information about the world. Here, we show how different types of information-gain …
The dopaminergic midbrain encodes the expected certainty about desired outcomes
P Schwartenbeck, THB FitzGerald, C Mathys… - Cerebral …, 2015 - academic.oup.com
Dopamine plays a key role in learning; however, its exact function in decision making and
choice remains unclear. Recently, we proposed a generic model based on active (Bayesian) …
choice remains unclear. Recently, we proposed a generic model based on active (Bayesian) …
On learning to think: Algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models
J Schmidhuber - arXiv preprint arXiv:1511.09249, 2015 - arxiv.org
This paper addresses the general problem of reinforcement learning (RL) in partially
observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned …
observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned …
[PDF][PDF] Boredom, information-seeking and exploration.
Any adaptive organism faces the choice between taking actions with known benefits
(exploitation), and sampling new actions to check for other, more valuable opportunities …
(exploitation), and sampling new actions to check for other, more valuable opportunities …
[HTML][HTML] Curiosity and the dynamics of optimal exploration
What drives our curiosity remains an elusive and hotly debated issue, with multiple
hypotheses proposed but a cohesive account yet to be established. This review discusses …
hypotheses proposed but a cohesive account yet to be established. This review discusses …
The minority report: some common assumptions to reconsider in the modelling of the brain and behaviour
S Edelman - Journal of Experimental & Theoretical Artificial …, 2016 - Taylor & Francis
Reverse-engineering the brain involves adopting and testing a hierarchy of working
hypotheses regarding the computational problems that it solves, the representations and …
hypotheses regarding the computational problems that it solves, the representations and …
Value systems for developmental cognitive robotics: A survey
K Merrick - Cognitive Systems Research, 2017 - Elsevier
This paper surveys value systems for developmental cognitive robotics. A value system
permits a biological brain to increase the likelihood of neural responses to selected external …
permits a biological brain to increase the likelihood of neural responses to selected external …